From 04571530bc4e4ac4e48c12266f65611cd57ab878 Mon Sep 17 00:00:00 2001 From: hedging8563 <45883076+hedging8563@users.noreply.github.com> Date: Thu, 9 Jul 2026 01:50:33 +0800 Subject: [PATCH 01/13] feat(tokenlab): add TokenLab provider --- README.md | 1 + litellm/__init__.py | 5 + litellm/constants.py | 2 + .../get_llm_provider_logic.py | 3 + litellm/llms/openai_like/json_loader.py | 8 + litellm/llms/openai_like/providers.json | 9 + ...odel_prices_and_context_window_backup.json | 3204 +++++++++++++++++ .../provider_endpoints_support_backup.json | 17 + litellm/types/utils.py | 1 + model_prices_and_context_window.json | 3204 +++++++++++++++++ provider_endpoints_support.json | 17 + .../openai_like/test_tokenlab_provider.py | 170 + 12 files changed, 6641 insertions(+) create mode 100644 tests/test_litellm/llms/openai_like/test_tokenlab_provider.py diff --git a/README.md b/README.md index 90d3e944fcc..ce31801009c 100644 --- a/README.md +++ b/README.md @@ -361,6 +361,7 @@ curl -X POST 'http://0.0.0.0:4000/v1/chat/completions' \ | [Text Completion Codestral (`text-completion-codestral`)](https://docs.litellm.ai/docs/providers/codestral) | ✅ | ✅ | ✅ | | | | | | | | | [Text Completion OpenAI (`text-completion-openai`)](https://docs.litellm.ai/docs/providers/text_completion_openai) | ✅ | ✅ | ✅ | | | ✅ | ✅ | ✅ | ✅ | | | [Together AI (`together_ai`)](https://docs.litellm.ai/docs/providers/togetherai) | ✅ | ✅ | ✅ | | | | | | | | +| [TokenLab (`tokenlab`)](https://docs.tokenlab.sh/integrations/litellm) | ✅ | ✅ | ✅ | ✅ | | | | | | | | [Topaz (`topaz`)](https://docs.litellm.ai/docs/providers/topaz) | ✅ | ✅ | ✅ | | | | | | | | | [Triton (`triton`)](https://docs.litellm.ai/docs/providers/triton-inference-server) | ✅ | ✅ | ✅ | | | | | | | | | [V0 (`v0`)](https://docs.litellm.ai/docs/providers/v0) | ✅ | ✅ | ✅ | | | | | | | | diff --git a/litellm/__init__.py b/litellm/__init__.py index 6e2a03b7c7c..0f2a968b20f 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -629,6 +629,7 @@ dashscope_models: Set = set() moonshot_models: Set = set() publicai_models: Set = set() darkbloom_models: Set = set() +tokenlab_models: Set = set() v0_models: Set = set() morph_models: Set = set() lambda_ai_models: Set = set() @@ -883,6 +884,8 @@ def add_known_models(model_cost_map: Optional[Dict] = None): publicai_models.add(key) elif value.get("litellm_provider") == "darkbloom": darkbloom_models.add(key) + elif value.get("litellm_provider") == "tokenlab": + tokenlab_models.add(key) elif value.get("litellm_provider") == "v0": v0_models.add(key) elif value.get("litellm_provider") == "morph": @@ -1032,6 +1035,7 @@ model_list = list( | moonshot_models | publicai_models | darkbloom_models + | tokenlab_models | v0_models | morph_models | lambda_ai_models @@ -1138,6 +1142,7 @@ models_by_provider: dict = { "moonshot": moonshot_models, "publicai": publicai_models, "darkbloom": darkbloom_models, + "tokenlab": tokenlab_models, "v0": v0_models, "morph": morph_models, "lambda_ai": lambda_ai_models, diff --git a/litellm/constants.py b/litellm/constants.py index 715d57e594d..bc578460845 100644 --- a/litellm/constants.py +++ b/litellm/constants.py @@ -714,6 +714,7 @@ openai_compatible_endpoints: List = [ "https://api.inference.wandb.ai/v1", "https://api.clarifai.com/v2/ext/openai/v1", "https://api.libertai.io/v1", + "https://api.tokenlab.sh/v1", "https://pinstripes.io/v1", "https://api.meta.ai/v1", ] @@ -781,6 +782,7 @@ openai_compatible_providers: List = [ "docker_model_runner", "ragflow", "pinstripes", # Pinstripes - JSON-configured provider + "tokenlab", # TokenLab - JSON-configured provider "darkbloom", "meta", # Meta Model API (Muse Spark) - JSON-configured provider ] diff --git a/litellm/litellm_core_utils/get_llm_provider_logic.py b/litellm/litellm_core_utils/get_llm_provider_logic.py index fa8ffe1ba1d..357ba2745aa 100644 --- a/litellm/litellm_core_utils/get_llm_provider_logic.py +++ b/litellm/litellm_core_utils/get_llm_provider_logic.py @@ -343,6 +343,9 @@ def get_llm_provider( elif endpoint == "https://api.inference.wandb.ai/v1": custom_llm_provider = "wandb" dynamic_api_key = get_secret_str("WANDB_API_KEY") + elif endpoint == "https://api.tokenlab.sh/v1": + custom_llm_provider = "tokenlab" + dynamic_api_key = get_secret_str("TOKENLAB_API_KEY") elif endpoint == "https://pinstripes.io/v1": custom_llm_provider = "pinstripes" dynamic_api_key = get_secret_str("PINSTRIPES_API_KEY") diff --git a/litellm/llms/openai_like/json_loader.py b/litellm/llms/openai_like/json_loader.py index 4640bb8a422..b0883f6b36b 100644 --- a/litellm/llms/openai_like/json_loader.py +++ b/litellm/llms/openai_like/json_loader.py @@ -73,6 +73,14 @@ class JSONProviderRegistry: return False return "/v1/responses" in provider.supported_endpoints + @classmethod + def supports_anthropic_messages_api(cls, slug: str) -> bool: + """Check if a JSON provider supports the Anthropic Messages API""" + provider = cls._providers.get(slug) + if provider is None: + return False + return "/v1/messages" in provider.supported_endpoints + @classmethod def list_providers(cls) -> list: """List all registered provider slugs""" diff --git a/litellm/llms/openai_like/providers.json b/litellm/llms/openai_like/providers.json index 164100d4194..59dfca54369 100644 --- a/litellm/llms/openai_like/providers.json +++ b/litellm/llms/openai_like/providers.json @@ -175,6 +175,15 @@ "base_class": "openai_gpt", "supported_endpoints": ["/v1/chat/completions", "/v1/responses", "/v1/messages"] }, + "tokenlab": { + "base_url": "https://api.tokenlab.sh/v1", + "api_key_env": "TOKENLAB_API_KEY", + "api_base_env": "TOKENLAB_API_BASE", + "param_mappings": { + "max_completion_tokens": "max_tokens" + }, + "supported_endpoints": ["/v1/chat/completions", "/v1/messages", "/v1/responses", "/v1/embeddings"] + }, "pinstripes": { "base_url": "https://pinstripes.io/v1", "api_key_env": "PINSTRIPES_API_KEY", diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2a269d693ec..636022182e3 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -44996,6 +44996,3210 @@ "supports_reasoning": false, "source": "https://pinstripes.io/pricing" }, + "tokenlab/allam-2-7b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 8e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/claude-fable-5": { + "cache_creation_input_token_cost": 8.125e-06, + "cache_read_input_token_cost": 6.5e-07, + "input_cost_per_token": 6.5e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.25e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-haiku-4-5": { + "cache_creation_input_token_cost": 8.125e-07, + "cache_read_input_token_cost": 6.5e-08, + "input_cost_per_token": 6.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.25e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-opus-4-6": { + "cache_creation_input_token_cost": 4.0625e-06, + "cache_read_input_token_cost": 3.25e-07, + "input_cost_per_token": 3.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.625e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-opus-4-7": { + "cache_creation_input_token_cost": 4.0625e-06, + "cache_read_input_token_cost": 3.25e-07, + "input_cost_per_token": 3.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.625e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-opus-4-8": { + "cache_creation_input_token_cost": 4.0625e-06, + "cache_read_input_token_cost": 3.25e-07, + "input_cost_per_token": 3.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.625e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-sonnet-4-6": { + "cache_creation_input_token_cost": 2.4375e-06, + "cache_read_input_token_cost": 1.95e-07, + "input_cost_per_token": 1.95e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 9.75e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-sonnet-5": { + "cache_creation_input_token_cost": 1.625e-06, + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 1.3e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/deepseek-v3": { + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/deepseek-v3-2": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 4.2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.94118e-09, + "input_cost_per_token": 1.4705882e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/deepseek-v4-pro": { + "cache_read_input_token_cost": 3.67647e-09, + "input_cost_per_token": 4.4117647e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 8.8235294e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-1.5-lite-32k": { + "cache_read_input_token_cost": 8.57143e-09, + "input_cost_per_token": 4.411765e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 8.823529e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-1.5-pro-32k": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-1.5-pro-32k-character": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 12288, + "max_tokens": 12288, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-1.5-vision-pro": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-1.6": { + "cache_read_input_token_cost": 3.602941e-08, + "input_cost_per_token": 1.7647059e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-1.6-flash": { + "cache_read_input_token_cost": 8.52941e-09, + "input_cost_per_token": 4.411765e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-1.6-vision": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-1.8": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-2.0-code": { + "cache_read_input_token_cost": 9.411765e-08, + "input_cost_per_token": 4.7058824e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 229376, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.35294118e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-2.0-lite": { + "cache_read_input_token_cost": 1.764706e-08, + "input_cost_per_token": 8.823529e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 229376, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.2941176e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-2.0-mini": { + "cache_read_input_token_cost": 5.88235e-09, + "input_cost_per_token": 2.941176e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 229376, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-2.0-pro": { + "cache_read_input_token_cost": 9.411765e-08, + "input_cost_per_token": 4.7058824e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 229376, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.35294118e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-2.1-pro": { + "cache_read_input_token_cost": 1.7647059e-07, + "input_cost_per_token": 8.8235294e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.41176471e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-2.1-turbo": { + "cache_read_input_token_cost": 8.823529e-08, + "input_cost_per_token": 4.4117647e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.20588235e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-character": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 98304, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-code": { + "cache_read_input_token_cost": 3.529412e-08, + "input_cost_per_token": 1.7647059e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-evolving": { + "cache_read_input_token_cost": 1.7647059e-07, + "input_cost_per_token": 8.8235294e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.41176471e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/farui-plus": { + "input_cost_per_token": 2.94117647e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 12000, + "max_output_tokens": 2000, + "max_tokens": 2000, + "mode": "chat", + "output_cost_per_token": 2.94117647e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/gemini-2.5-pro": { + "cache_read_input_token_cost": 6.25e-08, + "input_cost_per_token": 6.25e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 1.25e-08, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.5-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/glm-4.7": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/glm-5": { + "cache_read_input_token_cost": 1.1764706e-07, + "input_cost_per_token": 5.8823529e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.64705882e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/glm-5-turbo": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/glm-5.1": { + "cache_creation_input_token_cost": 1.10294118e-06, + "cache_read_input_token_cost": 1.7647059e-07, + "input_cost_per_token": 8.8235294e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.52941176e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/glm-5.2": { + "cache_read_input_token_cost": 2.9411765e-07, + "input_cost_per_token": 1.17647059e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.11764706e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/glm-5v-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-4.1-mini": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.12e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-4o": { + "cache_read_input_token_cost": 8.75e-07, + "input_cost_per_token": 1.75e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-4o-mini": { + "cache_read_input_token_cost": 5.25e-08, + "input_cost_per_token": 1.05e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 4.2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5": { + "cache_read_input_token_cost": 8.75e-08, + "input_cost_per_token": 8.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5-mini": { + "cache_read_input_token_cost": 1.75e-08, + "input_cost_per_token": 1.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5-nano": { + "cache_read_input_token_cost": 3.5e-09, + "input_cost_per_token": 3.5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5-pro": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00012, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5-search-api": { + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.1": { + "cache_read_input_token_cost": 8.75e-08, + "input_cost_per_token": 8.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.2": { + "cache_read_input_token_cost": 1.225e-07, + "input_cost_per_token": 1.225e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.8e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.2-pro": { + "cache_read_input_token_cost": 1.05e-05, + "input_cost_per_token": 2.1e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000168, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.225e-07, + "input_cost_per_token": 1.225e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.8e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.4": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.4-mini": { + "cache_read_input_token_cost": 2.25e-08, + "input_cost_per_token": 2.25e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.35e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.4-nano": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8.75e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.4-pro": { + "cache_read_input_token_cost": 3e-06, + "input_cost_per_token": 3e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00018, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.5": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.5-pro": { + "input_cost_per_token": 3e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00018, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-oss-120b": { + "cache_read_input_token_cost": 5.25e-08, + "input_cost_per_token": 1.05e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/gpt-oss-20b": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/grok-4-fast": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 2000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.1-fast": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 2000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.20": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.20-multi-agent": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.20-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.3": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-build-0.1": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 256000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/groq-compound": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/groq-compound-mini": { + "input_cost_per_token": 5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/hunyuan-role": { + "input_cost_per_token": 3.5294118e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 28672, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.41176471e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/hy-mt2-pro": { + "input_cost_per_token": 2.2058824e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6176471e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/hy3-preview": { + "cache_read_input_token_cost": 5.882353e-08, + "input_cost_per_token": 1.7647059e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.8823529e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/kimi-k2.5": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/kimi-k2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/kimi-k2.7-code-highspeed": { + "cache_read_input_token_cost": 3.8e-07, + "input_cost_per_token": 1.9e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2-flash": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2-omni": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2-pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/mimo-v2.5": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2.5-pro": { + "cache_read_input_token_cost": 2.0588235e-07, + "input_cost_per_token": 1.02941176e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.08823529e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/minimax-m2": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.1": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.1-highspeed": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.5": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.5-highspeed": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.7": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/minimax-m2.7-highspeed": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/minimax-m3": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/o1": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/o1-pro": { + "cache_read_input_token_cost": 7.5e-05, + "input_cost_per_token": 0.00015, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0006, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/o3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/o3-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/o4-mini": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 7.7e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 3.08e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/qwen-deep-research": { + "input_cost_per_token": 7.94117647e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.397058824e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-doc-turbo": { + "cache_creation_input_token_cost": 1.1029412e-07, + "cache_read_input_token_cost": 1.764706e-08, + "input_cost_per_token": 8.82353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 253952, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.4705882e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-flash": { + "cache_creation_input_token_cost": 2.852941e-08, + "cache_read_input_token_cost": 4.41176e-09, + "input_cost_per_token": 2.205882e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.2058823e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-flash-character": { + "cache_read_input_token_cost": 7.35294e-09, + "input_cost_per_token": 3.676471e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.2058823e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-max": { + "cache_read_input_token_cost": 7.058824e-08, + "input_cost_per_token": 3.5294117e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 30720, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.4117647e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-mt-flash": { + "input_cost_per_token": 1.0294118e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8676471e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-mt-lite": { + "input_cost_per_token": 8.82353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.3529412e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-mt-plus": { + "input_cost_per_token": 2.6470589e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-mt-turbo": { + "input_cost_per_token": 1.0294118e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8676471e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-omni-turbo": { + "cache_read_input_token_cost": 1.17647e-08, + "input_cost_per_token": 5.882353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.3529412e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen-omni-turbo-realtime": { + "input_cost_per_token": 2.3529412e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 9.4117647e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-plus": { + "cache_creation_input_token_cost": 1.4705882e-07, + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764705e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-plus-character": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764705e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-vl-ocr": { + "input_cost_per_token": 4.411764e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 30000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.352941e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen2.5-omni-7b": { + "input_cost_per_token": 8.82353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.5294117e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3-coder-flash": { + "cache_creation_input_token_cost": 1.8382353e-07, + "cache_read_input_token_cost": 2.941177e-08, + "input_cost_per_token": 1.4705882e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5.8823529e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3-livetranslate-flash": { + "input_cost_per_token": 1.47058824e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.47058824e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3-livetranslate-flash-realtime": { + "input_cost_per_token": 9.4117647e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.4117647e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3-omni-flash": { + "input_cost_per_token": 2.6470589e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.01470589e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3-omni-flash-realtime": { + "input_cost_per_token": 3.2352941e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.22058824e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3-vl-embedding": { + "input_cost_per_token": 1.0294118e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supports_vision": true + }, + "tokenlab/qwen3-vl-plus": { + "cache_creation_input_token_cost": 1.8382353e-07, + "cache_read_input_token_cost": 2.941177e-08, + "input_cost_per_token": 1.4705882e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 260096, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.47058824e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3.5-27b": { + "input_cost_per_token": 8.82353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 260096, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.0588236e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-flash": { + "cache_creation_input_token_cost": 3.676471e-08, + "cache_read_input_token_cost": 2.94117e-09, + "input_cost_per_token": 2.941177e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-livetranslate-flash-realtime": { + "input_cost_per_token": 5.88235294e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.470588236e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-ocr": { + "input_cost_per_token": 7.352941e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3.5-omni-flash": { + "input_cost_per_token": 2.64705882e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.05882353e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3.5-omni-flash-realtime": { + "input_cost_per_token": 3.97058824e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.573529412e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-omni-plus": { + "input_cost_per_token": 7.79411765e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.132352941e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3.5-omni-plus-realtime": { + "input_cost_per_token": 1.176470588e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.411764706e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-plus": { + "cache_creation_input_token_cost": 1.4705882e-07, + "cache_read_input_token_cost": 1.17647e-08, + "input_cost_per_token": 1.1764705e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.0588236e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.6-27b": { + "input_cost_per_token": 4.4117647e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.64705882e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.6-flash": { + "cache_creation_input_token_cost": 2.2058823e-07, + "cache_read_input_token_cost": 1.764706e-08, + "input_cost_per_token": 1.7647059e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.05882353e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.6-max-preview": { + "cache_read_input_token_cost": 1.475e-07, + "input_cost_per_token": 1.43264706e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 8.59632353e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/qwen3.6-plus": { + "cache_creation_input_token_cost": 3.6764706e-07, + "cache_read_input_token_cost": 2.941177e-08, + "input_cost_per_token": 2.9411765e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.76470588e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.7-max": { + "cache_creation_input_token_cost": 2.20588235e-06, + "cache_read_input_token_cost": 3.5294117e-07, + "input_cost_per_token": 1.76470588e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5.29411764e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.7-plus": { + "cache_creation_input_token_cost": 3.6764706e-07, + "cache_read_input_token_cost": 5.882353e-08, + "input_cost_per_token": 2.9411765e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/step-3.5-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/step-3.7-flash": { + "cache_read_input_token_cost": 3.970588e-08, + "input_cost_per_token": 1.9852941e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.19117647e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/text-embedding-v4": { + "input_cost_per_token": 7.352941e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/tongyi-intent-detect-v3": { + "input_cost_per_token": 5.882353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.4705882e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/tongyi-xiaomi-analysis-flash": { + "input_cost_per_token": 2.941177e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 28672, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.882353e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/tongyi-xiaomi-analysis-pro": { + "input_cost_per_token": 1.4705882e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 28672, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.9705883e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, "fallback_generalizations": { "rules": [ { diff --git a/litellm/provider_endpoints_support_backup.json b/litellm/provider_endpoints_support_backup.json index dd7712aabca..45fc4af1f70 100644 --- a/litellm/provider_endpoints_support_backup.json +++ b/litellm/provider_endpoints_support_backup.json @@ -1573,6 +1573,23 @@ "a2a": false } }, + "tokenlab": { + "display_name": "TokenLab (`tokenlab`)", + "url": "https://docs.tokenlab.sh/integrations/litellm", + "endpoints": { + "chat_completions": true, + "messages": true, + "responses": true, + "embeddings": true, + "image_generations": false, + "audio_transcriptions": false, + "audio_speech": false, + "moderations": false, + "batches": false, + "rerank": false, + "a2a": false + } + }, "nvidia_nim": { "display_name": "Nvidia NIM (`nvidia_nim`)", "url": "https://docs.litellm.ai/docs/providers/nvidia_nim", diff --git a/litellm/types/utils.py b/litellm/types/utils.py index 8a5acc24d19..a7577c8a2ca 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -3395,6 +3395,7 @@ class LlmProviders(str, Enum): PARASAIL = "parasail" XIAOMI_MIMO = "xiaomi_mimo" TENSORMESH = "tensormesh" + TOKENLAB = "tokenlab" LIBERTAI = "libertai" PINSTRIPES = "pinstripes" DARKBLOOM = "darkbloom" diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e79ddbe35d2..b9b80519be5 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -45229,6 +45229,3210 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/allam-2-7b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 8e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/claude-fable-5": { + "cache_creation_input_token_cost": 8.125e-06, + "cache_read_input_token_cost": 6.5e-07, + "input_cost_per_token": 6.5e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.25e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-haiku-4-5": { + "cache_creation_input_token_cost": 8.125e-07, + "cache_read_input_token_cost": 6.5e-08, + "input_cost_per_token": 6.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.25e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-opus-4-6": { + "cache_creation_input_token_cost": 4.0625e-06, + "cache_read_input_token_cost": 3.25e-07, + "input_cost_per_token": 3.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.625e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-opus-4-7": { + "cache_creation_input_token_cost": 4.0625e-06, + "cache_read_input_token_cost": 3.25e-07, + "input_cost_per_token": 3.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.625e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-opus-4-8": { + "cache_creation_input_token_cost": 4.0625e-06, + "cache_read_input_token_cost": 3.25e-07, + "input_cost_per_token": 3.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.625e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-sonnet-4-6": { + "cache_creation_input_token_cost": 2.4375e-06, + "cache_read_input_token_cost": 1.95e-07, + "input_cost_per_token": 1.95e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 9.75e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-sonnet-5": { + "cache_creation_input_token_cost": 1.625e-06, + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 1.3e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/deepseek-v3": { + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/deepseek-v3-2": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 4.2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.94118e-09, + "input_cost_per_token": 1.4705882e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/deepseek-v4-pro": { + "cache_read_input_token_cost": 3.67647e-09, + "input_cost_per_token": 4.4117647e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 8.8235294e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-1.5-lite-32k": { + "cache_read_input_token_cost": 8.57143e-09, + "input_cost_per_token": 4.411765e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 8.823529e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-1.5-pro-32k": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-1.5-pro-32k-character": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 12288, + "max_tokens": 12288, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-1.5-vision-pro": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-1.6": { + "cache_read_input_token_cost": 3.602941e-08, + "input_cost_per_token": 1.7647059e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-1.6-flash": { + "cache_read_input_token_cost": 8.52941e-09, + "input_cost_per_token": 4.411765e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-1.6-vision": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-1.8": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-2.0-code": { + "cache_read_input_token_cost": 9.411765e-08, + "input_cost_per_token": 4.7058824e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 229376, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.35294118e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-2.0-lite": { + "cache_read_input_token_cost": 1.764706e-08, + "input_cost_per_token": 8.823529e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 229376, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.2941176e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-2.0-mini": { + "cache_read_input_token_cost": 5.88235e-09, + "input_cost_per_token": 2.941176e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 229376, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-2.0-pro": { + "cache_read_input_token_cost": 9.411765e-08, + "input_cost_per_token": 4.7058824e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 229376, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.35294118e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-2.1-pro": { + "cache_read_input_token_cost": 1.7647059e-07, + "input_cost_per_token": 8.8235294e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.41176471e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-2.1-turbo": { + "cache_read_input_token_cost": 8.823529e-08, + "input_cost_per_token": 4.4117647e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.20588235e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-character": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764706e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 98304, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/doubao-seed-code": { + "cache_read_input_token_cost": 3.529412e-08, + "input_cost_per_token": 1.7647059e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/doubao-seed-evolving": { + "cache_read_input_token_cost": 1.7647059e-07, + "input_cost_per_token": 8.8235294e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.41176471e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/farui-plus": { + "input_cost_per_token": 2.94117647e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 12000, + "max_output_tokens": 2000, + "max_tokens": 2000, + "mode": "chat", + "output_cost_per_token": 2.94117647e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/gemini-2.5-pro": { + "cache_read_input_token_cost": 6.25e-08, + "input_cost_per_token": 6.25e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 1.25e-08, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.5-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/glm-4.7": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/glm-5": { + "cache_read_input_token_cost": 1.1764706e-07, + "input_cost_per_token": 5.8823529e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.64705882e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/glm-5-turbo": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/glm-5.1": { + "cache_creation_input_token_cost": 1.10294118e-06, + "cache_read_input_token_cost": 1.7647059e-07, + "input_cost_per_token": 8.8235294e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.52941176e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/glm-5.2": { + "cache_read_input_token_cost": 2.9411765e-07, + "input_cost_per_token": 1.17647059e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.11764706e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/glm-5v-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-4.1-mini": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.12e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-4o": { + "cache_read_input_token_cost": 8.75e-07, + "input_cost_per_token": 1.75e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-4o-mini": { + "cache_read_input_token_cost": 5.25e-08, + "input_cost_per_token": 1.05e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 4.2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5": { + "cache_read_input_token_cost": 8.75e-08, + "input_cost_per_token": 8.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5-mini": { + "cache_read_input_token_cost": 1.75e-08, + "input_cost_per_token": 1.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5-nano": { + "cache_read_input_token_cost": 3.5e-09, + "input_cost_per_token": 3.5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5-pro": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00012, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5-search-api": { + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.1": { + "cache_read_input_token_cost": 8.75e-08, + "input_cost_per_token": 8.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.2": { + "cache_read_input_token_cost": 1.225e-07, + "input_cost_per_token": 1.225e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.8e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.2-pro": { + "cache_read_input_token_cost": 1.05e-05, + "input_cost_per_token": 2.1e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000168, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.225e-07, + "input_cost_per_token": 1.225e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.8e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.4": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.4-mini": { + "cache_read_input_token_cost": 2.25e-08, + "input_cost_per_token": 2.25e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.35e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.4-nano": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8.75e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.4-pro": { + "cache_read_input_token_cost": 3e-06, + "input_cost_per_token": 3e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00018, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.5": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.5-pro": { + "input_cost_per_token": 3e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00018, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-oss-120b": { + "cache_read_input_token_cost": 5.25e-08, + "input_cost_per_token": 1.05e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/gpt-oss-20b": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/grok-4-fast": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 2000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.1-fast": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 2000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.20": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.20-multi-agent": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.20-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.3": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-build-0.1": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 256000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/groq-compound": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/groq-compound-mini": { + "input_cost_per_token": 5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/hunyuan-role": { + "input_cost_per_token": 3.5294118e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 28672, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.41176471e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/hy-mt2-pro": { + "input_cost_per_token": 2.2058824e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6176471e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/hy3-preview": { + "cache_read_input_token_cost": 5.882353e-08, + "input_cost_per_token": 1.7647059e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.8823529e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/kimi-k2.5": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/kimi-k2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/kimi-k2.7-code-highspeed": { + "cache_read_input_token_cost": 3.8e-07, + "input_cost_per_token": 1.9e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2-flash": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2-omni": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2-pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/mimo-v2.5": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2.5-pro": { + "cache_read_input_token_cost": 2.0588235e-07, + "input_cost_per_token": 1.02941176e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.08823529e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/minimax-m2": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.1": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.1-highspeed": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.5": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.5-highspeed": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 204800, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/minimax-m2.7": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/minimax-m2.7-highspeed": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/minimax-m3": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/o1": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/o1-pro": { + "cache_read_input_token_cost": 7.5e-05, + "input_cost_per_token": 0.00015, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0006, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/o3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/o3-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/o4-mini": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 7.7e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 3.08e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/qwen-deep-research": { + "input_cost_per_token": 7.94117647e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.397058824e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-doc-turbo": { + "cache_creation_input_token_cost": 1.1029412e-07, + "cache_read_input_token_cost": 1.764706e-08, + "input_cost_per_token": 8.82353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 253952, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.4705882e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-flash": { + "cache_creation_input_token_cost": 2.852941e-08, + "cache_read_input_token_cost": 4.41176e-09, + "input_cost_per_token": 2.205882e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.2058823e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-flash-character": { + "cache_read_input_token_cost": 7.35294e-09, + "input_cost_per_token": 3.676471e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.2058823e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-max": { + "cache_read_input_token_cost": 7.058824e-08, + "input_cost_per_token": 3.5294117e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 30720, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.4117647e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-mt-flash": { + "input_cost_per_token": 1.0294118e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8676471e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-mt-lite": { + "input_cost_per_token": 8.82353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.3529412e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-mt-plus": { + "input_cost_per_token": 2.6470589e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-mt-turbo": { + "input_cost_per_token": 1.0294118e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8676471e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-omni-turbo": { + "cache_read_input_token_cost": 1.17647e-08, + "input_cost_per_token": 5.882353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.3529412e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen-omni-turbo-realtime": { + "input_cost_per_token": 2.3529412e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 9.4117647e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen-plus": { + "cache_creation_input_token_cost": 1.4705882e-07, + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764705e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-plus-character": { + "cache_read_input_token_cost": 2.352941e-08, + "input_cost_per_token": 1.1764705e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen-vl-ocr": { + "input_cost_per_token": 4.411764e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 30000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.352941e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen2.5-omni-7b": { + "input_cost_per_token": 8.82353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.5294117e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3-coder-flash": { + "cache_creation_input_token_cost": 1.8382353e-07, + "cache_read_input_token_cost": 2.941177e-08, + "input_cost_per_token": 1.4705882e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5.8823529e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3-livetranslate-flash": { + "input_cost_per_token": 1.47058824e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.47058824e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3-livetranslate-flash-realtime": { + "input_cost_per_token": 9.4117647e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.4117647e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3-omni-flash": { + "input_cost_per_token": 2.6470589e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.01470589e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3-omni-flash-realtime": { + "input_cost_per_token": 3.2352941e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.22058824e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3-vl-embedding": { + "input_cost_per_token": 1.0294118e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supports_vision": true + }, + "tokenlab/qwen3-vl-plus": { + "cache_creation_input_token_cost": 1.8382353e-07, + "cache_read_input_token_cost": 2.941177e-08, + "input_cost_per_token": 1.4705882e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 260096, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.47058824e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3.5-27b": { + "input_cost_per_token": 8.82353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 260096, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.0588236e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-flash": { + "cache_creation_input_token_cost": 3.676471e-08, + "cache_read_input_token_cost": 2.94117e-09, + "input_cost_per_token": 2.941177e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-livetranslate-flash-realtime": { + "input_cost_per_token": 5.88235294e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.470588236e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-ocr": { + "input_cost_per_token": 7.352941e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 49152, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.9411765e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3.5-omni-flash": { + "input_cost_per_token": 2.64705882e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.05882353e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3.5-omni-flash-realtime": { + "input_cost_per_token": 3.97058824e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.573529412e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-omni-plus": { + "input_cost_per_token": 7.79411765e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.132352941e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_vision": true + }, + "tokenlab/qwen3.5-omni-plus-realtime": { + "input_cost_per_token": 1.176470588e-05, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.411764706e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.5-plus": { + "cache_creation_input_token_cost": 1.4705882e-07, + "cache_read_input_token_cost": 1.17647e-08, + "input_cost_per_token": 1.1764705e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.0588236e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.6-27b": { + "input_cost_per_token": 4.4117647e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.64705882e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.6-flash": { + "cache_creation_input_token_cost": 2.2058823e-07, + "cache_read_input_token_cost": 1.764706e-08, + "input_cost_per_token": 1.7647059e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.05882353e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.6-max-preview": { + "cache_read_input_token_cost": 1.475e-07, + "input_cost_per_token": 1.43264706e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 8.59632353e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/qwen3.6-plus": { + "cache_creation_input_token_cost": 3.6764706e-07, + "cache_read_input_token_cost": 2.941177e-08, + "input_cost_per_token": 2.9411765e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.76470588e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.7-max": { + "cache_creation_input_token_cost": 2.20588235e-06, + "cache_read_input_token_cost": 3.5294117e-07, + "input_cost_per_token": 1.76470588e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5.29411764e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/qwen3.7-plus": { + "cache_creation_input_token_cost": 3.6764706e-07, + "cache_read_input_token_cost": 5.882353e-08, + "input_cost_per_token": 2.9411765e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.17647059e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true + }, + "tokenlab/step-3.5-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/step-3.7-flash": { + "cache_read_input_token_cost": 3.970588e-08, + "input_cost_per_token": 1.9852941e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.19117647e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/text-embedding-v4": { + "input_cost_per_token": 7.352941e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/tongyi-intent-detect-v3": { + "input_cost_per_token": 5.882353e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.4705882e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/tongyi-xiaomi-analysis-flash": { + "input_cost_per_token": 2.941177e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 28672, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.882353e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, + "tokenlab/tongyi-xiaomi-analysis-pro": { + "input_cost_per_token": 1.4705882e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 28672, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.9705883e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_native_streaming": true, + "supports_system_messages": true + }, "fallback_generalizations": { "rules": [ { diff --git a/provider_endpoints_support.json b/provider_endpoints_support.json index 65db63dc045..3d50aa150cc 100644 --- a/provider_endpoints_support.json +++ b/provider_endpoints_support.json @@ -2294,6 +2294,23 @@ "a2a": false } }, + "tokenlab": { + "display_name": "TokenLab (`tokenlab`)", + "url": "https://docs.tokenlab.sh/integrations/litellm", + "endpoints": { + "chat_completions": true, + "messages": true, + "responses": true, + "embeddings": true, + "image_generations": false, + "audio_transcriptions": false, + "audio_speech": false, + "moderations": false, + "batches": false, + "rerank": false, + "a2a": false + } + }, "tensormesh": { "display_name": "Tensormesh (`tensormesh`)", "url": "https://docs.litellm.ai/docs/providers/tensormesh", diff --git a/tests/test_litellm/llms/openai_like/test_tokenlab_provider.py b/tests/test_litellm/llms/openai_like/test_tokenlab_provider.py new file mode 100644 index 00000000000..06894718198 --- /dev/null +++ b/tests/test_litellm/llms/openai_like/test_tokenlab_provider.py @@ -0,0 +1,170 @@ +import pytest + +import litellm + + +TOKENLAB_API_BASE = "https://api.tokenlab.sh/v1" +TOKENLAB_SAMPLE_MODELS = [ + "tokenlab/gpt-5.5", + "tokenlab/claude-opus-4-8", + "tokenlab/gemini-3.5-flash", + "tokenlab/deepseek-v4-pro", + "tokenlab/qwen3.7-max", + "tokenlab/text-embedding-3-small", +] + + +def test_tokenlab_json_registry(): + from litellm.llms.openai_like.json_loader import JSONProviderRegistry + + assert litellm.LlmProviders.TOKENLAB.value == "tokenlab" + assert litellm.LlmProviders("tokenlab") == litellm.LlmProviders.TOKENLAB + assert JSONProviderRegistry.exists("tokenlab") + config = JSONProviderRegistry.get("tokenlab") + assert config is not None + assert config.base_url == TOKENLAB_API_BASE + assert config.api_key_env == "TOKENLAB_API_KEY" + assert config.api_base_env == "TOKENLAB_API_BASE" + assert config.param_mappings["max_completion_tokens"] == "max_tokens" + assert config.supported_endpoints == [ + "/v1/chat/completions", + "/v1/messages", + "/v1/responses", + "/v1/embeddings", + ] + assert JSONProviderRegistry.supports_responses_api("tokenlab") is True + assert JSONProviderRegistry.supports_anthropic_messages_api("tokenlab") is True + + +def test_tokenlab_provider_detection_by_prefix(): + from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider + + model, provider, _, api_base = get_llm_provider("tokenlab/gpt-5.5") + + assert model == "gpt-5.5" + assert provider == "tokenlab" + assert api_base == TOKENLAB_API_BASE + + +def test_tokenlab_api_base_override(): + from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider + + _, provider, api_key, api_base = get_llm_provider( + model="tokenlab/gpt-5.5", + api_base="https://custom.tokenlab.example/v1", + api_key="sk-test", + ) + + assert provider == "tokenlab" + assert api_base == "https://custom.tokenlab.example/v1" + assert api_key == "sk-test" + + +def test_tokenlab_url_autodetection(): + from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider + + _, provider, _, api_base = get_llm_provider( + model="gpt-5.5", + api_base=TOKENLAB_API_BASE, + ) + + assert provider == "tokenlab" + assert api_base == TOKENLAB_API_BASE + + +def test_tokenlab_chat_complete_url(): + from litellm.llms.openai_like.dynamic_config import create_config_class + from litellm.llms.openai_like.json_loader import JSONProviderRegistry + + config = create_config_class(JSONProviderRegistry.get("tokenlab"))() + + assert ( + config.get_complete_url( + api_base=None, + api_key=None, + model="gpt-5.5", + optional_params={}, + litellm_params={}, + ) + == "https://api.tokenlab.sh/v1/chat/completions" + ) + + +def test_tokenlab_responses_api_config(): + from litellm.llms.openai.responses.transformation import OpenAIResponsesAPIConfig + from litellm.utils import ProviderConfigManager + + config = ProviderConfigManager.get_provider_responses_api_config( + provider="tokenlab", + model="tokenlab/gpt-5.5", + ) + + assert isinstance(config, OpenAIResponsesAPIConfig) + assert config.custom_llm_provider == "tokenlab" + assert config.get_complete_url(api_base=None, litellm_params={}) == "https://api.tokenlab.sh/v1/responses" + + +def test_tokenlab_anthropic_messages_config(): + from litellm.llms.openai_like.messages.transformation import ( + OpenAILikeAnthropicMessagesConfig, + ) + from litellm.utils import ProviderConfigManager + + config = ProviderConfigManager.get_provider_anthropic_messages_config( + provider=litellm.LlmProviders.TOKENLAB, + model="claude-opus-4-8", + ) + + assert isinstance(config, OpenAILikeAnthropicMessagesConfig) + assert ( + config.get_complete_url( + api_base=TOKENLAB_API_BASE, + api_key="sk-test", + model="claude-opus-4-8", + optional_params={}, + litellm_params={}, + ) + == "https://api.tokenlab.sh/v1/messages" + ) + + +class TestTokenLabCostMap: + @pytest.fixture(autouse=True) + def _use_local_model_cost_map(self, monkeypatch): + original_model_cost = litellm.model_cost + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + litellm.model_cost = litellm.get_model_cost_map(url="") + litellm.get_model_info.cache_clear() + try: + yield + finally: + litellm.model_cost = original_model_cost + litellm.get_model_info.cache_clear() + + def test_sample_models_registered(self): + for model in TOKENLAB_SAMPLE_MODELS: + info = litellm.get_model_info(model) + assert info["litellm_provider"] == "tokenlab" + assert info["mode"] in {"chat", "embedding"} + + def test_claude_models_advertise_messages_endpoint(self): + endpoints = litellm.model_cost["tokenlab/claude-opus-4-8"]["supported_endpoints"] + assert "/v1/messages" in endpoints + + def test_chat_cost_is_wired(self): + prompt_cost, completion_cost = litellm.cost_per_token( + model="tokenlab/gpt-5.5", + prompt_tokens=1_000_000, + completion_tokens=1_000_000, + ) + assert prompt_cost == pytest.approx(1.5) + assert completion_cost == pytest.approx(9.0) + + def test_embedding_cost_is_wired(self): + prompt_cost, completion_cost = litellm.cost_per_token( + model="tokenlab/text-embedding-3-small", + prompt_tokens=1_000_000, + completion_tokens=0, + ) + assert prompt_cost == pytest.approx(0.02) + assert completion_cost == 0 From ede53bd65bb200325cfaae8e0c21be8738ce83cd Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Thu, 9 Jul 2026 14:42:01 +0800 Subject: [PATCH 02/13] fix(tokenlab): align model metadata with schema --- ...odel_prices_and_context_window_backup.json | 29 ++++++++++--------- model_prices_and_context_window.json | 29 ++++++++++--------- .../openai_like/test_tokenlab_provider.py | 10 +++++-- 3 files changed, 38 insertions(+), 30 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 636022182e3..2cf6c205e84 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -45025,8 +45025,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45038,8 +45037,10 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_adaptive_thinking": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -45057,8 +45058,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45089,8 +45089,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45121,8 +45120,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45134,8 +45132,10 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_adaptive_thinking": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -45153,8 +45153,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45166,8 +45165,10 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_adaptive_thinking": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -45185,8 +45186,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45217,8 +45217,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45230,8 +45229,10 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_adaptive_thinking": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index b9b80519be5..821670ffd74 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -45258,8 +45258,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45271,8 +45270,10 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_adaptive_thinking": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -45290,8 +45291,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45322,8 +45322,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45354,8 +45353,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45367,8 +45365,10 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_adaptive_thinking": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -45386,8 +45386,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45399,8 +45398,10 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_adaptive_thinking": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -45418,8 +45419,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45450,8 +45450,7 @@ "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/messages" + "/v1/responses" ], "supported_modalities": [ "text", @@ -45463,8 +45462,10 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_adaptive_thinking": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true diff --git a/tests/test_litellm/llms/openai_like/test_tokenlab_provider.py b/tests/test_litellm/llms/openai_like/test_tokenlab_provider.py index 06894718198..b459f9ba119 100644 --- a/tests/test_litellm/llms/openai_like/test_tokenlab_provider.py +++ b/tests/test_litellm/llms/openai_like/test_tokenlab_provider.py @@ -147,9 +147,15 @@ class TestTokenLabCostMap: assert info["litellm_provider"] == "tokenlab" assert info["mode"] in {"chat", "embedding"} - def test_claude_models_advertise_messages_endpoint(self): + def test_claude_model_cost_map_keeps_schema_supported_endpoints(self): + from litellm.llms.openai_like.json_loader import JSONProviderRegistry + endpoints = litellm.model_cost["tokenlab/claude-opus-4-8"]["supported_endpoints"] - assert "/v1/messages" in endpoints + assert endpoints == ["/v1/chat/completions", "/v1/responses"] + + provider_config = JSONProviderRegistry.get("tokenlab") + assert provider_config is not None + assert "/v1/messages" in provider_config.supported_endpoints def test_chat_cost_is_wired(self): prompt_cost, completion_cost = litellm.cost_per_token( From 3a9257d3c65c6eb1d14936fc2b6800c81090894c Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Sun, 16 Aug 2026 05:17:03 +0800 Subject: [PATCH 03/13] fix(tokenlab): satisfy provider quality gates --- litellm/__init__.py | 2 +- litellm/litellm_core_utils/get_llm_provider_logic.py | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/litellm/__init__.py b/litellm/__init__.py index 3b8e2a20a96..8a1f40514da 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -647,7 +647,7 @@ dashscope_models: Set = set() moonshot_models: Set = set() publicai_models: Set = set() darkbloom_models: Set = set() -tokenlab_models: Set = set() +tokenlab_models: Set = set() # mutable-ok: populated while loading the static model registry v0_models: Set = set() morph_models: Set = set() lambda_ai_models: Set = set() diff --git a/litellm/litellm_core_utils/get_llm_provider_logic.py b/litellm/litellm_core_utils/get_llm_provider_logic.py index b990dc3febb..06ee0416710 100644 --- a/litellm/litellm_core_utils/get_llm_provider_logic.py +++ b/litellm/litellm_core_utils/get_llm_provider_logic.py @@ -345,7 +345,8 @@ def get_llm_provider( dynamic_api_key = get_secret_str("WANDB_API_KEY") elif endpoint == "https://api.tokenlab.sh/v1": custom_llm_provider = "tokenlab" - dynamic_api_key = get_secret_str("TOKENLAB_API_KEY") + tokenlab_config: Final = JSONProviderRegistry.get("tokenlab") + dynamic_api_key = get_secret_str(tokenlab_config.api_key_env) if tokenlab_config else None elif endpoint == "https://pinstripes.io/v1": custom_llm_provider = "pinstripes" dynamic_api_key = get_secret_str("PINSTRIPES_API_KEY") From 85f05b0626a604f0ebc67ff56303ebfa503c8406 Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Fri, 2 Oct 2026 05:52:17 +0800 Subject: [PATCH 04/13] docs: update TokenLab documentation links TokenLab's documentation moved from docs.tokenlab.sh to tokenlab.sh/docs. The old addresses redirect; these links now point at the pages directly. Co-Authored-By: Claude Opus 5.5 --- README.md | 2 +- litellm/provider_endpoints_support_backup.json | 2 +- provider_endpoints_support.json | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index e79d341ee50..0d48689af26 100644 --- a/README.md +++ b/README.md @@ -361,7 +361,7 @@ curl -X POST 'http://0.0.0.0:4000/v1/chat/completions' \ | [Text Completion Codestral (`text-completion-codestral`)](https://docs.litellm.ai/docs/providers/codestral) | ✅ | ✅ | ✅ | | | | | | | | | [Text Completion OpenAI (`text-completion-openai`)](https://docs.litellm.ai/docs/providers/text_completion_openai) | ✅ | ✅ | ✅ | | | ✅ | ✅ | ✅ | ✅ | | | [Together AI (`together_ai`)](https://docs.litellm.ai/docs/providers/togetherai) | ✅ | ✅ | ✅ | | | | | | | | -| [TokenLab (`tokenlab`)](https://docs.tokenlab.sh/integrations/litellm) | ✅ | ✅ | ✅ | ✅ | | | | | | | +| [TokenLab (`tokenlab`)](https://tokenlab.sh/docs/en/integrations/litellm) | ✅ | ✅ | ✅ | ✅ | | | | | | | | [Topaz (`topaz`)](https://docs.litellm.ai/docs/providers/topaz) | ✅ | ✅ | ✅ | | | | | | | | | [Triton (`triton`)](https://docs.litellm.ai/docs/providers/triton-inference-server) | ✅ | ✅ | ✅ | | | | | | | | | [V0 (`v0`)](https://docs.litellm.ai/docs/providers/v0) | ✅ | ✅ | ✅ | | | | | | | | diff --git a/litellm/provider_endpoints_support_backup.json b/litellm/provider_endpoints_support_backup.json index 45fc4af1f70..28b0eb27d94 100644 --- a/litellm/provider_endpoints_support_backup.json +++ b/litellm/provider_endpoints_support_backup.json @@ -1575,7 +1575,7 @@ }, "tokenlab": { "display_name": "TokenLab (`tokenlab`)", - "url": "https://docs.tokenlab.sh/integrations/litellm", + "url": "https://tokenlab.sh/docs/en/integrations/litellm", "endpoints": { "chat_completions": true, "messages": true, diff --git a/provider_endpoints_support.json b/provider_endpoints_support.json index 281e9fede57..fe0f127d540 100644 --- a/provider_endpoints_support.json +++ b/provider_endpoints_support.json @@ -2296,7 +2296,7 @@ }, "tokenlab": { "display_name": "TokenLab (`tokenlab`)", - "url": "https://docs.tokenlab.sh/integrations/litellm", + "url": "https://tokenlab.sh/docs/en/integrations/litellm", "endpoints": { "chat_completions": true, "messages": true, From 4787c048a99e5cd60b0e369c1c3169bcfe789e85 Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Fri, 2 Oct 2026 06:39:03 +0800 Subject: [PATCH 05/13] test(tokenlab): follow the unit test layout and drop an unused suppression The provider test moves next to the other OpenAI-like provider tests under tests/unit, which is where the CI shards look for them. The `mutable-ok` marker on `tokenlab_models` suppressed nothing, so the type discipline gate reported it as LIT013; the line now matches its neighbours. Co-Authored-By: Claude Opus 5.5 --- litellm/__init__.py | 2 +- .../llms/openai_like/test_tokenlab_provider.py | 0 2 files changed, 1 insertion(+), 1 deletion(-) rename tests/{test_litellm => unit}/llms/openai_like/test_tokenlab_provider.py (100%) diff --git a/litellm/__init__.py b/litellm/__init__.py index a6951df31fc..69da370bc06 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -687,7 +687,7 @@ qwen_ai_platform_models: Set = set() moonshot_models: Set = set() publicai_models: Set = set() darkbloom_models: Set = set() -tokenlab_models: Set = set() # mutable-ok: populated while loading the static model registry +tokenlab_models: Set = set() v0_models: Set = set() morph_models: Set = set() lambda_ai_models: Set = set() diff --git a/tests/test_litellm/llms/openai_like/test_tokenlab_provider.py b/tests/unit/llms/openai_like/test_tokenlab_provider.py similarity index 100% rename from tests/test_litellm/llms/openai_like/test_tokenlab_provider.py rename to tests/unit/llms/openai_like/test_tokenlab_provider.py From 9da5e2d4befd0f4b7395d572fde007f0db5d8550 Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Fri, 2 Oct 2026 09:09:55 +0800 Subject: [PATCH 06/13] fix(tokenlab): list the provider in Add Model and use the shared base-url lookup TokenLab gets an entry in provider_create_fields.json, which the Add Model dropdown test requires for every backend provider. The explicit endpoint branch in get_llm_provider is removed: JSONProviderRegistry.get_by_base_url already resolves a JSON-configured provider from its base url, and the removed branch declared a Final inside the loop, which the type gate counts. Co-Authored-By: Claude Opus 5.5 --- .../get_llm_provider_logic.py | 4 --- .../provider_create_fields.json | 28 +++++++++++++++++++ 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/litellm/litellm_core_utils/get_llm_provider_logic.py b/litellm/litellm_core_utils/get_llm_provider_logic.py index b01aa1a6b2c..d4642ae2aad 100644 --- a/litellm/litellm_core_utils/get_llm_provider_logic.py +++ b/litellm/litellm_core_utils/get_llm_provider_logic.py @@ -389,10 +389,6 @@ def get_llm_provider( elif endpoint == "https://api.inference.wandb.ai/v1": custom_llm_provider = "wandb" dynamic_api_key = get_secret_str("WANDB_API_KEY") - elif endpoint == "https://api.tokenlab.sh/v1": - custom_llm_provider = "tokenlab" - tokenlab_config: Final = JSONProviderRegistry.get("tokenlab") - dynamic_api_key = get_secret_str(tokenlab_config.api_key_env) if tokenlab_config else None elif endpoint == "https://pinstripes.io/v1": custom_llm_provider = "pinstripes" dynamic_api_key = get_secret_str("PINSTRIPES_API_KEY") diff --git a/litellm/proxy/public_endpoints/provider_create_fields.json b/litellm/proxy/public_endpoints/provider_create_fields.json index 11d2ff61b95..3e71a3ff243 100644 --- a/litellm/proxy/public_endpoints/provider_create_fields.json +++ b/litellm/proxy/public_endpoints/provider_create_fields.json @@ -3207,6 +3207,34 @@ ], "default_model_placeholder": "gpt-3.5-turbo" }, + { + "provider": "TOKENLAB", + "provider_display_name": "TokenLab", + "litellm_provider": "tokenlab", + "credential_fields": [ + { + "key": "api_base", + "label": "API Base", + "placeholder": "https://api.tokenlab.sh/v1", + "tooltip": null, + "required": false, + "field_type": "text", + "options": null, + "default_value": null + }, + { + "key": "api_key", + "label": "API Key", + "placeholder": null, + "tooltip": null, + "required": true, + "field_type": "password", + "options": null, + "default_value": null + } + ], + "default_model_placeholder": "tokenlab/gpt-5.5" + }, { "provider": "TOPAZ", "provider_display_name": "Topaz", From b5f6bffd25cc29332c828e738ddc3fa013b0ec89 Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Sat, 3 Oct 2026 05:47:56 +0800 Subject: [PATCH 07/13] fix(tokenlab): add the model set without new type findings The lint job failed on the basedpyright budget: the new provider branch passed an untyped key to an untyped set, which counts as one more reportUnknownArgumentType. The set is now Set[str] and the branch narrows the key with isinstance, so the TokenLab lines add no unknown-argument, unknown-variable or missing-type-argument findings. Model cost map keys are always strings, so behaviour is unchanged. Co-Authored-By: Claude Opus 5.5 --- litellm/__init__.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/litellm/__init__.py b/litellm/__init__.py index 69da370bc06..ab14dce3502 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -687,7 +687,7 @@ qwen_ai_platform_models: Set = set() moonshot_models: Set = set() publicai_models: Set = set() darkbloom_models: Set = set() -tokenlab_models: Set = set() +tokenlab_models: Set[str] = set() v0_models: Set = set() morph_models: Set = set() lambda_ai_models: Set = set() @@ -953,7 +953,7 @@ def _populate_provider_model_sets(model_cost_map: Dict) -> None: publicai_models.add(key) elif value.get("litellm_provider") == "darkbloom": darkbloom_models.add(key) - elif value.get("litellm_provider") == "tokenlab": + elif value.get("litellm_provider") == "tokenlab" and isinstance(key, str): tokenlab_models.add(key) elif value.get("litellm_provider") == "v0": v0_models.add(key) From d01252cfbc92ea9e21ba1d682edefd04de36667e Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Sat, 3 Oct 2026 06:17:10 +0800 Subject: [PATCH 08/13] fix(tokenlab): refresh the model cost entries from the live catalog The TokenLab entries were taken from an earlier catalog. 35 of them named models TokenLab no longer serves, 62 carried old prices, and 13 claimed tool, vision, caching or reasoning support the catalog does not list. Prices, cache prices, token limits and those four capability flags now follow https://api.tokenlab.sh/v1/models; entries for removed models are gone. The cost tests read the expected price from the cost map instead of repeating a number that changes with the catalog. Co-Authored-By: Claude Opus 5.5 --- ...odel_prices_and_context_window_backup.json | 1167 ++++------------- model_prices_and_context_window.json | 1167 ++++------------- .../openai_like/test_tokenlab_provider.py | 12 +- 3 files changed, 459 insertions(+), 1887 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 03088fef846..6a057fe8be1 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -60806,15 +60806,15 @@ "supports_system_messages": true }, "tokenlab/claude-fable-5": { - "cache_creation_input_token_cost": 8.125e-06, - "cache_read_input_token_cost": 6.5e-07, - "input_cost_per_token": 6.5e-06, + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.25e-05, + "output_cost_per_token": 1.5e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60839,15 +60839,15 @@ "supports_vision": true }, "tokenlab/claude-haiku-4-5": { - "cache_creation_input_token_cost": 8.125e-07, - "cache_read_input_token_cost": 6.5e-08, - "input_cost_per_token": 6.5e-07, + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "tokenlab", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 3.25e-06, + "output_cost_per_token": 1.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60870,15 +60870,15 @@ "supports_vision": true }, "tokenlab/claude-opus-4-6": { - "cache_creation_input_token_cost": 4.0625e-06, - "cache_read_input_token_cost": 3.25e-07, - "input_cost_per_token": 3.25e-06, + "cache_creation_input_token_cost": 1.875e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.625e-05, + "output_cost_per_token": 7.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60901,15 +60901,15 @@ "supports_vision": true }, "tokenlab/claude-opus-4-7": { - "cache_creation_input_token_cost": 4.0625e-06, - "cache_read_input_token_cost": 3.25e-07, - "input_cost_per_token": 3.25e-06, + "cache_creation_input_token_cost": 1.875e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.625e-05, + "output_cost_per_token": 7.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60934,15 +60934,15 @@ "supports_vision": true }, "tokenlab/claude-opus-4-8": { - "cache_creation_input_token_cost": 4.0625e-06, - "cache_read_input_token_cost": 3.25e-07, - "input_cost_per_token": 3.25e-06, + "cache_creation_input_token_cost": 1.875e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.625e-05, + "output_cost_per_token": 7.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60967,15 +60967,15 @@ "supports_vision": true }, "tokenlab/claude-sonnet-4-6": { - "cache_creation_input_token_cost": 2.4375e-06, - "cache_read_input_token_cost": 1.95e-07, - "input_cost_per_token": 1.95e-06, + "cache_creation_input_token_cost": 1.125e-06, + "cache_read_input_token_cost": 9e-08, + "input_cost_per_token": 9e-07, "litellm_provider": "tokenlab", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 9.75e-06, + "output_cost_per_token": 4.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60998,15 +60998,15 @@ "supports_vision": true }, "tokenlab/claude-sonnet-5": { - "cache_creation_input_token_cost": 1.625e-06, - "cache_read_input_token_cost": 1.3e-07, - "input_cost_per_token": 1.3e-06, + "cache_creation_input_token_cost": 1.125e-06, + "cache_read_input_token_cost": 9e-08, + "input_cost_per_token": 9e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6.5e-06, + "output_cost_per_token": 4.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61030,57 +61030,15 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/deepseek-v3": { - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 1000000, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/deepseek-v3-2": { - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2.8e-08, - "input_cost_per_token": 2.8e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 4.2e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/deepseek-v4-flash": { - "cache_read_input_token_cost": 2.94118e-09, - "input_cost_per_token": 1.4705882e-07, + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 6e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61094,14 +61052,15 @@ "supports_tool_choice": true }, "tokenlab/deepseek-v4-pro": { - "cache_read_input_token_cost": 3.67647e-09, - "input_cost_per_token": 4.4117647e-07, + "cache_creation_input_token_cost": 6.6e-07, + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 6.6e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 8.8235294e-07, + "output_cost_per_token": 1.98e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61114,177 +61073,8 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/doubao-1.5-lite-32k": { - "cache_read_input_token_cost": 8.57143e-09, - "input_cost_per_token": 4.411765e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 8.823529e-08, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-1.5-pro-32k": { - "cache_read_input_token_cost": 2.2e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-1.5-pro-32k-character": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 32768, - "max_output_tokens": 12288, - "max_tokens": 12288, - "mode": "chat", - "output_cost_per_token": 2.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-1.5-vision-pro": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/doubao-seed-1.6": { - "cache_read_input_token_cost": 3.602941e-08, - "input_cost_per_token": 1.7647059e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.17647059e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-seed-1.6-flash": { - "cache_read_input_token_cost": 8.52941e-09, - "input_cost_per_token": 4.411765e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-seed-1.6-vision": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.17647059e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/doubao-seed-1.8": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.17647059e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/doubao-seed-2.0-code": { + "cache_creation_input_token_cost": 4.7058824e-07, "cache_read_input_token_cost": 9.411765e-08, "input_cost_per_token": 4.7058824e-07, "litellm_provider": "tokenlab", @@ -61307,14 +61097,15 @@ "supports_tool_choice": true }, "tokenlab/doubao-seed-2.0-lite": { - "cache_read_input_token_cost": 1.764706e-08, - "input_cost_per_token": 8.823529e-08, + "cache_creation_input_token_cost": 2.5e-07, + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2.5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 229376, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 5.2941176e-07, + "output_cost_per_token": 2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61337,14 +61128,15 @@ "supports_vision": true }, "tokenlab/doubao-seed-2.0-mini": { - "cache_read_input_token_cost": 5.88235e-09, - "input_cost_per_token": 2.941176e-08, + "cache_creation_input_token_cost": 1e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1e-07, "litellm_provider": "tokenlab", "max_input_tokens": 229376, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 4e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61367,6 +61159,7 @@ "supports_vision": true }, "tokenlab/doubao-seed-2.0-pro": { + "cache_creation_input_token_cost": 4.7058824e-07, "cache_read_input_token_cost": 9.411765e-08, "input_cost_per_token": 4.7058824e-07, "litellm_provider": "tokenlab", @@ -61427,14 +61220,15 @@ "supports_vision": true }, "tokenlab/doubao-seed-2.1-turbo": { - "cache_read_input_token_cost": 8.823529e-08, - "input_cost_per_token": 4.4117647e-07, + "cache_creation_input_token_cost": 5e-07, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.20588235e-06, + "output_cost_per_token": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61486,25 +61280,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/doubao-seed-code": { - "cache_read_input_token_cost": 3.529412e-08, - "input_cost_per_token": 1.7647059e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.17647059e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/doubao-seed-evolving": { "cache_read_input_token_cost": 1.7647059e-07, "input_cost_per_token": 8.8235294e-07, @@ -61535,22 +61310,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/farui-plus": { - "input_cost_per_token": 2.94117647e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 12000, - "max_output_tokens": 2000, - "max_tokens": 2000, - "mode": "chat", - "output_cost_per_token": 2.94117647e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, "tokenlab/gemini-2.5-pro": { "cache_read_input_token_cost": 6.25e-08, "input_cost_per_token": 6.25e-07, @@ -61667,15 +61426,16 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/glm-4.7": { - "cache_read_input_token_cost": 1.25e-07, + "tokenlab/glm-5": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1e-06, "litellm_provider": "tokenlab", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 3.2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61683,26 +61443,10 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/glm-5": { - "cache_read_input_token_cost": 1.1764706e-07, - "input_cost_per_token": 5.8823529e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.64705882e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, "tokenlab/glm-5-turbo": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.4e-07, @@ -61725,39 +61469,46 @@ "supports_tool_choice": true }, "tokenlab/glm-5.1": { - "cache_creation_input_token_cost": 1.10294118e-06, - "cache_read_input_token_cost": 1.7647059e-07, - "input_cost_per_token": 8.8235294e-07, + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.52941176e-06, + "output_cost_per_token": 4.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true }, "tokenlab/glm-5.2": { - "cache_read_input_token_cost": 2.9411765e-07, - "input_cost_per_token": 1.17647059e-06, + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.11764706e-06, + "output_cost_per_token": 4.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true }, "tokenlab/glm-5v-turbo": { "cache_read_input_token_cost": 2.4e-07, @@ -62133,20 +61884,21 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "tokenlab/gpt-5.4": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, "litellm_provider": "tokenlab", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 1.05e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62169,14 +61921,14 @@ "supports_vision": true }, "tokenlab/gpt-5.4-mini": { - "cache_read_input_token_cost": 2.25e-08, - "input_cost_per_token": 2.25e-07, + "cache_read_input_token_cost": 5.25e-08, + "input_cost_per_token": 5.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.35e-06, + "output_cost_per_token": 3.15e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62311,14 +62063,14 @@ "supports_vision": true }, "tokenlab/gpt-oss-120b": { - "cache_read_input_token_cost": 5.25e-08, - "input_cost_per_token": 1.05e-07, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4.2e-07, + "output_cost_per_token": 6e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62351,73 +62103,15 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/grok-4-fast": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 2000000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/grok-4.1-fast": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 2000000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/grok-4.20": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62440,14 +62134,14 @@ "supports_vision": true }, "tokenlab/grok-4.20-multi-agent": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62470,14 +62164,14 @@ "supports_vision": true }, "tokenlab/grok-4.20-non-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62499,14 +62193,14 @@ "supports_vision": true }, "tokenlab/grok-4.3": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62529,14 +62223,14 @@ "supports_vision": true }, "tokenlab/grok-build-0.1": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 256000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 1e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62558,42 +62252,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/groq-compound": { - "input_cost_per_token": 5.9e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/groq-compound-mini": { - "input_cost_per_token": 5e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 8e-08, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/hunyuan-role": { "input_cost_per_token": 3.5294118e-07, "litellm_provider": "tokenlab", @@ -62611,13 +62269,13 @@ "supports_system_messages": true }, "tokenlab/hy-mt2-pro": { - "input_cost_per_token": 2.2058824e-07, + "input_cost_per_token": 7.4e-08, "litellm_provider": "tokenlab", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 6.6176471e-07, + "output_cost_per_token": 2.95e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62626,28 +62284,6 @@ "supports_native_streaming": true, "supports_system_messages": true }, - "tokenlab/hy3-preview": { - "cache_read_input_token_cost": 5.882353e-08, - "input_cost_per_token": 1.7647059e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 196608, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5.8823529e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/kimi-k2.5": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 6e-07, @@ -62662,8 +62298,12 @@ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, @@ -62679,8 +62319,12 @@ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, @@ -62740,89 +62384,16 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/mimo-v2-flash": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/mimo-v2-omni": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/mimo-v2-pro": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/mimo-v2.5": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4e-07, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 2.8e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62842,21 +62413,25 @@ "supports_vision": true }, "tokenlab/mimo-v2.5-pro": { - "cache_read_input_token_cost": 2.0588235e-07, - "input_cost_per_token": 1.02941176e-06, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 4.35e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 3.08823529e-06, + "output_cost_per_token": 8.7e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/minimax-m2": { "cache_creation_input_token_cost": 3.75e-07, @@ -62920,27 +62495,6 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/minimax-m2.5": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 204800, - "max_output_tokens": 204800, - "max_tokens": 204800, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/minimax-m2.5-highspeed": { "cache_creation_input_token_cost": 3.75e-07, "cache_read_input_token_cost": 3e-08, @@ -63020,77 +62574,16 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/o1": { - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 7.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/o1-pro": { - "cache_read_input_token_cost": 7.5e-05, - "input_cost_per_token": 0.00015, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 0.0006, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/o3": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, + "cache_read_input_token_cost": 3.5e-07, + "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 8e-06, + "output_cost_per_token": 5.6e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63112,85 +62605,16 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/o3-mini": { - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 5.5e-07, - "input_cost_per_token": 1.1e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 4.4e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/o4-mini": { - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 7.7e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 3.08e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/qwen-deep-research": { - "input_cost_per_token": 7.94117647e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2.397058824e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, "tokenlab/qwen-doc-turbo": { - "cache_creation_input_token_cost": 1.1029412e-07, - "cache_read_input_token_cost": 1.764706e-08, - "input_cost_per_token": 8.82353e-08, + "cache_creation_input_token_cost": 1.10294117647e-07, + "cache_read_input_token_cost": 1.7647058824e-08, + "input_cost_per_token": 8.8235294117e-08, "litellm_provider": "tokenlab", "max_input_tokens": 253952, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.4705882e-07, + "output_cost_per_token": 1.47058823529e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63201,15 +62625,15 @@ "supports_system_messages": true }, "tokenlab/qwen-flash": { - "cache_creation_input_token_cost": 2.852941e-08, - "cache_read_input_token_cost": 4.41176e-09, - "input_cost_per_token": 2.205882e-08, + "cache_creation_input_token_cost": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 5e-08, "litellm_provider": "tokenlab", "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.2058823e-07, + "output_cost_per_token": 4e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63220,14 +62644,14 @@ "supports_system_messages": true }, "tokenlab/qwen-flash-character": { - "cache_read_input_token_cost": 7.35294e-09, - "input_cost_per_token": 3.676471e-08, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 5e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2.2058823e-07, + "output_cost_per_token": 4e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63238,14 +62662,14 @@ "supports_system_messages": true }, "tokenlab/qwen-max": { - "cache_read_input_token_cost": 7.058824e-08, - "input_cost_per_token": 3.5294117e-07, + "cache_read_input_token_cost": 3.2e-07, + "input_cost_per_token": 1.6e-06, "litellm_provider": "tokenlab", "max_input_tokens": 30720, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.4117647e-06, + "output_cost_per_token": 6.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63256,13 +62680,13 @@ "supports_system_messages": true }, "tokenlab/qwen-mt-flash": { - "input_cost_per_token": 1.0294118e-07, + "input_cost_per_token": 1.6e-07, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.8676471e-07, + "output_cost_per_token": 4.9e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63272,13 +62696,13 @@ "supports_system_messages": true }, "tokenlab/qwen-mt-lite": { - "input_cost_per_token": 8.82353e-08, + "input_cost_per_token": 1.2e-07, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.3529412e-07, + "output_cost_per_token": 3.6e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63288,71 +62712,13 @@ "supports_system_messages": true }, "tokenlab/qwen-mt-plus": { - "input_cost_per_token": 2.6470589e-07, + "input_cost_per_token": 2.46e-06, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, - "tokenlab/qwen-mt-turbo": { - "input_cost_per_token": 1.0294118e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.8676471e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, - "tokenlab/qwen-omni-turbo": { - "cache_read_input_token_cost": 1.17647e-08, - "input_cost_per_token": 5.882353e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 30720, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.3529412e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_vision": true - }, - "tokenlab/qwen-omni-turbo-realtime": { - "input_cost_per_token": 2.3529412e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 30720, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 9.4117647e-07, + "output_cost_per_token": 7.37e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63362,15 +62728,13 @@ "supports_system_messages": true }, "tokenlab/qwen-plus": { - "cache_creation_input_token_cost": 1.4705882e-07, - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764705e-07, + "input_cost_per_token": 4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 1.2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63381,14 +62745,14 @@ "supports_system_messages": true }, "tokenlab/qwen-plus-character": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764705e-07, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 1.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63399,37 +62763,13 @@ "supports_system_messages": true }, "tokenlab/qwen-vl-ocr": { - "input_cost_per_token": 4.411764e-08, + "input_cost_per_token": 7e-08, "litellm_provider": "tokenlab", "max_input_tokens": 30000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.352941e-08, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_vision": true - }, - "tokenlab/qwen2.5-omni-7b": { - "input_cost_per_token": 8.82353e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 30720, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.5294117e-07, + "output_cost_per_token": 1.6e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63447,15 +62787,15 @@ "supports_vision": true }, "tokenlab/qwen3-coder-flash": { - "cache_creation_input_token_cost": 1.8382353e-07, - "cache_read_input_token_cost": 2.941177e-08, - "input_cost_per_token": 1.4705882e-07, + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "tokenlab", "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 5.8823529e-07, + "output_cost_per_token": 1.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63479,32 +62819,17 @@ "/v1/responses" ], "supports_native_streaming": true, - "supports_system_messages": true - }, - "tokenlab/qwen3-livetranslate-flash-realtime": { - "input_cost_per_token": 9.4117647e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 49152, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 9.4117647e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_vision": true }, "tokenlab/qwen3-omni-flash": { - "input_cost_per_token": 2.6470589e-07, + "input_cost_per_token": 4.3e-07, "litellm_provider": "tokenlab", "max_input_tokens": 49152, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1.01470589e-06, + "output_cost_per_token": 1.66e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63521,24 +62846,8 @@ "supports_system_messages": true, "supports_vision": true }, - "tokenlab/qwen3-omni-flash-realtime": { - "input_cost_per_token": 3.2352941e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 49152, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.22058824e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, "tokenlab/qwen3-vl-embedding": { - "input_cost_per_token": 1.0294118e-07, + "input_cost_per_token": 1.02941176471e-07, "litellm_provider": "tokenlab", "max_input_tokens": 32000, "max_tokens": 32000, @@ -63551,15 +62860,15 @@ "supports_vision": true }, "tokenlab/qwen3-vl-plus": { - "cache_creation_input_token_cost": 1.8382353e-07, - "cache_read_input_token_cost": 2.941177e-08, - "input_cost_per_token": 1.4705882e-07, + "cache_creation_input_token_cost": 2.5e-07, + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, "litellm_provider": "tokenlab", "max_input_tokens": 260096, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.47058824e-06, + "output_cost_per_token": 1.6e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63578,13 +62887,13 @@ "supports_vision": true }, "tokenlab/qwen3.5-27b": { - "input_cost_per_token": 8.82353e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "tokenlab", "max_input_tokens": 260096, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 7.0588236e-07, + "output_cost_per_token": 2.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63594,15 +62903,15 @@ "supports_system_messages": true }, "tokenlab/qwen3.5-flash": { - "cache_creation_input_token_cost": 3.676471e-08, - "cache_read_input_token_cost": 2.94117e-09, - "input_cost_per_token": 2.941177e-08, + "cache_creation_input_token_cost": 1.25e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, "litellm_provider": "tokenlab", "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 4e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63626,16 +62935,17 @@ "/v1/responses" ], "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_vision": true }, "tokenlab/qwen3.5-ocr": { - "input_cost_per_token": 7.352941e-08, + "input_cost_per_token": 7.3529411765e-08, "litellm_provider": "tokenlab", "max_input_tokens": 49152, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 2.94117647059e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63653,13 +62963,13 @@ "supports_vision": true }, "tokenlab/qwen3.5-omni-flash": { - "input_cost_per_token": 2.64705882e-06, + "input_cost_per_token": 4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.05882353e-05, + "output_cost_per_token": 2.2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63677,29 +62987,32 @@ "supports_vision": true }, "tokenlab/qwen3.5-omni-flash-realtime": { - "input_cost_per_token": 3.97058824e-06, + "input_cost_per_token": 5.5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.573529412e-05, + "output_cost_per_token": 3.3e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/qwen3.5-omni-plus": { - "input_cost_per_token": 7.79411765e-06, + "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 3.132352941e-05, + "output_cost_per_token": 8.3e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63717,31 +63030,34 @@ "supports_vision": true }, "tokenlab/qwen3.5-omni-plus-realtime": { - "input_cost_per_token": 1.176470588e-05, + "input_cost_per_token": 2.1e-06, "litellm_provider": "tokenlab", "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4.411764706e-05, + "output_cost_per_token": 1.24e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/qwen3.5-plus": { - "cache_creation_input_token_cost": 1.4705882e-07, - "cache_read_input_token_cost": 1.17647e-08, - "input_cost_per_token": 1.1764705e-07, + "cache_creation_input_token_cost": 5e-07, + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 7.0588236e-07, + "output_cost_per_token": 2.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63752,42 +63068,25 @@ "supports_system_messages": true }, "tokenlab/qwen3.6-27b": { - "input_cost_per_token": 4.4117647e-07, + "input_cost_per_token": 6e-07, "litellm_provider": "tokenlab", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.64705882e-06, + "output_cost_per_token": 3.6e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true - }, - "tokenlab/qwen3.6-flash": { - "cache_creation_input_token_cost": 2.2058823e-07, - "cache_read_input_token_cost": 1.764706e-08, - "input_cost_per_token": 1.7647059e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 991808, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.05882353e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/qwen3.6-max-preview": { - "cache_read_input_token_cost": 1.475e-07, "input_cost_per_token": 1.43264706e-06, "litellm_provider": "tokenlab", "max_input_tokens": 262144, @@ -63805,35 +63104,16 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/qwen3.6-plus": { - "cache_creation_input_token_cost": 3.6764706e-07, - "cache_read_input_token_cost": 2.941177e-08, - "input_cost_per_token": 2.9411765e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 991808, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.76470588e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true - }, "tokenlab/qwen3.7-max": { - "cache_creation_input_token_cost": 2.20588235e-06, - "cache_read_input_token_cost": 3.5294117e-07, - "input_cost_per_token": 1.76470588e-06, + "cache_creation_input_token_cost": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 5.29411764e-06, + "output_cost_per_token": 7.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63844,15 +63124,15 @@ "supports_system_messages": true }, "tokenlab/qwen3.7-plus": { - "cache_creation_input_token_cost": 3.6764706e-07, - "cache_read_input_token_cost": 5.882353e-08, - "input_cost_per_token": 2.9411765e-07, + "cache_creation_input_token_cost": 5e-07, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.17647059e-06, + "output_cost_per_token": 1.6e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63882,24 +63162,27 @@ "supports_tool_choice": true }, "tokenlab/step-3.7-flash": { - "cache_read_input_token_cost": 3.970588e-08, - "input_cost_per_token": 1.9852941e-07, + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, "litellm_provider": "tokenlab", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.19117647e-06, + "output_cost_per_token": 1.15e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true }, "tokenlab/text-embedding-3-large": { - "input_cost_per_token": 1.3e-07, + "input_cost_per_token": 9.1e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8191, "max_tokens": 8191, @@ -63911,7 +63194,7 @@ ] }, "tokenlab/text-embedding-3-small": { - "input_cost_per_token": 2e-08, + "input_cost_per_token": 1.4e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8191, "max_tokens": 8191, @@ -63935,7 +63218,7 @@ ] }, "tokenlab/text-embedding-v4": { - "input_cost_per_token": 7.352941e-08, + "input_cost_per_token": 7e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_tokens": 8192, @@ -63947,13 +63230,13 @@ ] }, "tokenlab/tongyi-intent-detect-v3": { - "input_cost_per_token": 5.882353e-08, + "input_cost_per_token": 5.8823529412e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.4705882e-07, + "output_cost_per_token": 1.47058823529e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63963,13 +63246,13 @@ "supports_system_messages": true }, "tokenlab/tongyi-xiaomi-analysis-flash": { - "input_cost_per_token": 2.941177e-08, + "input_cost_per_token": 2.9411764705e-08, "litellm_provider": "tokenlab", "max_input_tokens": 28672, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 5.882353e-08, + "output_cost_per_token": 5.8823529412e-08, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63979,13 +63262,13 @@ "supports_system_messages": true }, "tokenlab/tongyi-xiaomi-analysis-pro": { - "input_cost_per_token": 1.4705882e-07, + "input_cost_per_token": 1.47058823529e-07, "litellm_provider": "tokenlab", "max_input_tokens": 28672, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.9705883e-07, + "output_cost_per_token": 3.97058823529e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 03088fef846..6a057fe8be1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -60806,15 +60806,15 @@ "supports_system_messages": true }, "tokenlab/claude-fable-5": { - "cache_creation_input_token_cost": 8.125e-06, - "cache_read_input_token_cost": 6.5e-07, - "input_cost_per_token": 6.5e-06, + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.25e-05, + "output_cost_per_token": 1.5e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60839,15 +60839,15 @@ "supports_vision": true }, "tokenlab/claude-haiku-4-5": { - "cache_creation_input_token_cost": 8.125e-07, - "cache_read_input_token_cost": 6.5e-08, - "input_cost_per_token": 6.5e-07, + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "tokenlab", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 3.25e-06, + "output_cost_per_token": 1.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60870,15 +60870,15 @@ "supports_vision": true }, "tokenlab/claude-opus-4-6": { - "cache_creation_input_token_cost": 4.0625e-06, - "cache_read_input_token_cost": 3.25e-07, - "input_cost_per_token": 3.25e-06, + "cache_creation_input_token_cost": 1.875e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.625e-05, + "output_cost_per_token": 7.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60901,15 +60901,15 @@ "supports_vision": true }, "tokenlab/claude-opus-4-7": { - "cache_creation_input_token_cost": 4.0625e-06, - "cache_read_input_token_cost": 3.25e-07, - "input_cost_per_token": 3.25e-06, + "cache_creation_input_token_cost": 1.875e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.625e-05, + "output_cost_per_token": 7.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60934,15 +60934,15 @@ "supports_vision": true }, "tokenlab/claude-opus-4-8": { - "cache_creation_input_token_cost": 4.0625e-06, - "cache_read_input_token_cost": 3.25e-07, - "input_cost_per_token": 3.25e-06, + "cache_creation_input_token_cost": 1.875e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.625e-05, + "output_cost_per_token": 7.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60967,15 +60967,15 @@ "supports_vision": true }, "tokenlab/claude-sonnet-4-6": { - "cache_creation_input_token_cost": 2.4375e-06, - "cache_read_input_token_cost": 1.95e-07, - "input_cost_per_token": 1.95e-06, + "cache_creation_input_token_cost": 1.125e-06, + "cache_read_input_token_cost": 9e-08, + "input_cost_per_token": 9e-07, "litellm_provider": "tokenlab", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 9.75e-06, + "output_cost_per_token": 4.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -60998,15 +60998,15 @@ "supports_vision": true }, "tokenlab/claude-sonnet-5": { - "cache_creation_input_token_cost": 1.625e-06, - "cache_read_input_token_cost": 1.3e-07, - "input_cost_per_token": 1.3e-06, + "cache_creation_input_token_cost": 1.125e-06, + "cache_read_input_token_cost": 9e-08, + "input_cost_per_token": 9e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6.5e-06, + "output_cost_per_token": 4.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61030,57 +61030,15 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/deepseek-v3": { - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 1000000, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/deepseek-v3-2": { - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2.8e-08, - "input_cost_per_token": 2.8e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 4.2e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/deepseek-v4-flash": { - "cache_read_input_token_cost": 2.94118e-09, - "input_cost_per_token": 1.4705882e-07, + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 6e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61094,14 +61052,15 @@ "supports_tool_choice": true }, "tokenlab/deepseek-v4-pro": { - "cache_read_input_token_cost": 3.67647e-09, - "input_cost_per_token": 4.4117647e-07, + "cache_creation_input_token_cost": 6.6e-07, + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 6.6e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 8.8235294e-07, + "output_cost_per_token": 1.98e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61114,177 +61073,8 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/doubao-1.5-lite-32k": { - "cache_read_input_token_cost": 8.57143e-09, - "input_cost_per_token": 4.411765e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 8.823529e-08, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-1.5-pro-32k": { - "cache_read_input_token_cost": 2.2e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-1.5-pro-32k-character": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 32768, - "max_output_tokens": 12288, - "max_tokens": 12288, - "mode": "chat", - "output_cost_per_token": 2.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-1.5-vision-pro": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/doubao-seed-1.6": { - "cache_read_input_token_cost": 3.602941e-08, - "input_cost_per_token": 1.7647059e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.17647059e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-seed-1.6-flash": { - "cache_read_input_token_cost": 8.52941e-09, - "input_cost_per_token": 4.411765e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/doubao-seed-1.6-vision": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.17647059e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/doubao-seed-1.8": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764706e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.17647059e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/doubao-seed-2.0-code": { + "cache_creation_input_token_cost": 4.7058824e-07, "cache_read_input_token_cost": 9.411765e-08, "input_cost_per_token": 4.7058824e-07, "litellm_provider": "tokenlab", @@ -61307,14 +61097,15 @@ "supports_tool_choice": true }, "tokenlab/doubao-seed-2.0-lite": { - "cache_read_input_token_cost": 1.764706e-08, - "input_cost_per_token": 8.823529e-08, + "cache_creation_input_token_cost": 2.5e-07, + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2.5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 229376, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 5.2941176e-07, + "output_cost_per_token": 2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61337,14 +61128,15 @@ "supports_vision": true }, "tokenlab/doubao-seed-2.0-mini": { - "cache_read_input_token_cost": 5.88235e-09, - "input_cost_per_token": 2.941176e-08, + "cache_creation_input_token_cost": 1e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1e-07, "litellm_provider": "tokenlab", "max_input_tokens": 229376, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 4e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61367,6 +61159,7 @@ "supports_vision": true }, "tokenlab/doubao-seed-2.0-pro": { + "cache_creation_input_token_cost": 4.7058824e-07, "cache_read_input_token_cost": 9.411765e-08, "input_cost_per_token": 4.7058824e-07, "litellm_provider": "tokenlab", @@ -61427,14 +61220,15 @@ "supports_vision": true }, "tokenlab/doubao-seed-2.1-turbo": { - "cache_read_input_token_cost": 8.823529e-08, - "input_cost_per_token": 4.4117647e-07, + "cache_creation_input_token_cost": 5e-07, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.20588235e-06, + "output_cost_per_token": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61486,25 +61280,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/doubao-seed-code": { - "cache_read_input_token_cost": 3.529412e-08, - "input_cost_per_token": 1.7647059e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.17647059e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/doubao-seed-evolving": { "cache_read_input_token_cost": 1.7647059e-07, "input_cost_per_token": 8.8235294e-07, @@ -61535,22 +61310,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/farui-plus": { - "input_cost_per_token": 2.94117647e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 12000, - "max_output_tokens": 2000, - "max_tokens": 2000, - "mode": "chat", - "output_cost_per_token": 2.94117647e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, "tokenlab/gemini-2.5-pro": { "cache_read_input_token_cost": 6.25e-08, "input_cost_per_token": 6.25e-07, @@ -61667,15 +61426,16 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/glm-4.7": { - "cache_read_input_token_cost": 1.25e-07, + "tokenlab/glm-5": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1e-06, "litellm_provider": "tokenlab", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 3.2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61683,26 +61443,10 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/glm-5": { - "cache_read_input_token_cost": 1.1764706e-07, - "input_cost_per_token": 5.8823529e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.64705882e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, "tokenlab/glm-5-turbo": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.4e-07, @@ -61725,39 +61469,46 @@ "supports_tool_choice": true }, "tokenlab/glm-5.1": { - "cache_creation_input_token_cost": 1.10294118e-06, - "cache_read_input_token_cost": 1.7647059e-07, - "input_cost_per_token": 8.8235294e-07, + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.52941176e-06, + "output_cost_per_token": 4.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true }, "tokenlab/glm-5.2": { - "cache_read_input_token_cost": 2.9411765e-07, - "input_cost_per_token": 1.17647059e-06, + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.11764706e-06, + "output_cost_per_token": 4.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true }, "tokenlab/glm-5v-turbo": { "cache_read_input_token_cost": 2.4e-07, @@ -62133,20 +61884,21 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "tokenlab/gpt-5.4": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, "litellm_provider": "tokenlab", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 1.05e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62169,14 +61921,14 @@ "supports_vision": true }, "tokenlab/gpt-5.4-mini": { - "cache_read_input_token_cost": 2.25e-08, - "input_cost_per_token": 2.25e-07, + "cache_read_input_token_cost": 5.25e-08, + "input_cost_per_token": 5.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.35e-06, + "output_cost_per_token": 3.15e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62311,14 +62063,14 @@ "supports_vision": true }, "tokenlab/gpt-oss-120b": { - "cache_read_input_token_cost": 5.25e-08, - "input_cost_per_token": 1.05e-07, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4.2e-07, + "output_cost_per_token": 6e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62351,73 +62103,15 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/grok-4-fast": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 2000000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/grok-4.1-fast": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 2000000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/grok-4.20": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62440,14 +62134,14 @@ "supports_vision": true }, "tokenlab/grok-4.20-multi-agent": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62470,14 +62164,14 @@ "supports_vision": true }, "tokenlab/grok-4.20-non-reasoning": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62499,14 +62193,14 @@ "supports_vision": true }, "tokenlab/grok-4.3": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 6.25e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62529,14 +62223,14 @@ "supports_vision": true }, "tokenlab/grok-build-0.1": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 256000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 1e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62558,42 +62252,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/groq-compound": { - "input_cost_per_token": 5.9e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/groq-compound-mini": { - "input_cost_per_token": 5e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 8e-08, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/hunyuan-role": { "input_cost_per_token": 3.5294118e-07, "litellm_provider": "tokenlab", @@ -62611,13 +62269,13 @@ "supports_system_messages": true }, "tokenlab/hy-mt2-pro": { - "input_cost_per_token": 2.2058824e-07, + "input_cost_per_token": 7.4e-08, "litellm_provider": "tokenlab", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 6.6176471e-07, + "output_cost_per_token": 2.95e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62626,28 +62284,6 @@ "supports_native_streaming": true, "supports_system_messages": true }, - "tokenlab/hy3-preview": { - "cache_read_input_token_cost": 5.882353e-08, - "input_cost_per_token": 1.7647059e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 196608, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5.8823529e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/kimi-k2.5": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 6e-07, @@ -62662,8 +62298,12 @@ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, @@ -62679,8 +62319,12 @@ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, @@ -62740,89 +62384,16 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/mimo-v2-flash": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/mimo-v2-omni": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/mimo-v2-pro": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/mimo-v2.5": { - "cache_read_input_token_cost": 8e-08, - "input_cost_per_token": 4e-07, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 2.8e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62842,21 +62413,25 @@ "supports_vision": true }, "tokenlab/mimo-v2.5-pro": { - "cache_read_input_token_cost": 2.0588235e-07, - "input_cost_per_token": 1.02941176e-06, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 4.35e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 3.08823529e-06, + "output_cost_per_token": 8.7e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/minimax-m2": { "cache_creation_input_token_cost": 3.75e-07, @@ -62920,27 +62495,6 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/minimax-m2.5": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 204800, - "max_output_tokens": 204800, - "max_tokens": 204800, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/minimax-m2.5-highspeed": { "cache_creation_input_token_cost": 3.75e-07, "cache_read_input_token_cost": 3e-08, @@ -63020,77 +62574,16 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/o1": { - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 7.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/o1-pro": { - "cache_read_input_token_cost": 7.5e-05, - "input_cost_per_token": 0.00015, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 0.0006, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/o3": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, + "cache_read_input_token_cost": 3.5e-07, + "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 8e-06, + "output_cost_per_token": 5.6e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63112,85 +62605,16 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/o3-mini": { - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 5.5e-07, - "input_cost_per_token": 1.1e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 4.4e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "tokenlab/o4-mini": { - "cache_read_input_token_cost": 1.925e-07, - "input_cost_per_token": 7.7e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 3.08e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/qwen-deep-research": { - "input_cost_per_token": 7.94117647e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2.397058824e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, "tokenlab/qwen-doc-turbo": { - "cache_creation_input_token_cost": 1.1029412e-07, - "cache_read_input_token_cost": 1.764706e-08, - "input_cost_per_token": 8.82353e-08, + "cache_creation_input_token_cost": 1.10294117647e-07, + "cache_read_input_token_cost": 1.7647058824e-08, + "input_cost_per_token": 8.8235294117e-08, "litellm_provider": "tokenlab", "max_input_tokens": 253952, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.4705882e-07, + "output_cost_per_token": 1.47058823529e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63201,15 +62625,15 @@ "supports_system_messages": true }, "tokenlab/qwen-flash": { - "cache_creation_input_token_cost": 2.852941e-08, - "cache_read_input_token_cost": 4.41176e-09, - "input_cost_per_token": 2.205882e-08, + "cache_creation_input_token_cost": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 5e-08, "litellm_provider": "tokenlab", "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.2058823e-07, + "output_cost_per_token": 4e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63220,14 +62644,14 @@ "supports_system_messages": true }, "tokenlab/qwen-flash-character": { - "cache_read_input_token_cost": 7.35294e-09, - "input_cost_per_token": 3.676471e-08, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 5e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2.2058823e-07, + "output_cost_per_token": 4e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63238,14 +62662,14 @@ "supports_system_messages": true }, "tokenlab/qwen-max": { - "cache_read_input_token_cost": 7.058824e-08, - "input_cost_per_token": 3.5294117e-07, + "cache_read_input_token_cost": 3.2e-07, + "input_cost_per_token": 1.6e-06, "litellm_provider": "tokenlab", "max_input_tokens": 30720, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.4117647e-06, + "output_cost_per_token": 6.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63256,13 +62680,13 @@ "supports_system_messages": true }, "tokenlab/qwen-mt-flash": { - "input_cost_per_token": 1.0294118e-07, + "input_cost_per_token": 1.6e-07, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.8676471e-07, + "output_cost_per_token": 4.9e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63272,13 +62696,13 @@ "supports_system_messages": true }, "tokenlab/qwen-mt-lite": { - "input_cost_per_token": 8.82353e-08, + "input_cost_per_token": 1.2e-07, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.3529412e-07, + "output_cost_per_token": 3.6e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63288,71 +62712,13 @@ "supports_system_messages": true }, "tokenlab/qwen-mt-plus": { - "input_cost_per_token": 2.6470589e-07, + "input_cost_per_token": 2.46e-06, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.9411765e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, - "tokenlab/qwen-mt-turbo": { - "input_cost_per_token": 1.0294118e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.8676471e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, - "tokenlab/qwen-omni-turbo": { - "cache_read_input_token_cost": 1.17647e-08, - "input_cost_per_token": 5.882353e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 30720, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.3529412e-07, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_vision": true - }, - "tokenlab/qwen-omni-turbo-realtime": { - "input_cost_per_token": 2.3529412e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 30720, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 9.4117647e-07, + "output_cost_per_token": 7.37e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63362,15 +62728,13 @@ "supports_system_messages": true }, "tokenlab/qwen-plus": { - "cache_creation_input_token_cost": 1.4705882e-07, - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764705e-07, + "input_cost_per_token": 4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 1.2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63381,14 +62745,14 @@ "supports_system_messages": true }, "tokenlab/qwen-plus-character": { - "cache_read_input_token_cost": 2.352941e-08, - "input_cost_per_token": 1.1764705e-07, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 1.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63399,37 +62763,13 @@ "supports_system_messages": true }, "tokenlab/qwen-vl-ocr": { - "input_cost_per_token": 4.411764e-08, + "input_cost_per_token": 7e-08, "litellm_provider": "tokenlab", "max_input_tokens": 30000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.352941e-08, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_vision": true - }, - "tokenlab/qwen2.5-omni-7b": { - "input_cost_per_token": 8.82353e-08, - "litellm_provider": "tokenlab", - "max_input_tokens": 30720, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.5294117e-07, + "output_cost_per_token": 1.6e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63447,15 +62787,15 @@ "supports_vision": true }, "tokenlab/qwen3-coder-flash": { - "cache_creation_input_token_cost": 1.8382353e-07, - "cache_read_input_token_cost": 2.941177e-08, - "input_cost_per_token": 1.4705882e-07, + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "tokenlab", "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 5.8823529e-07, + "output_cost_per_token": 1.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63479,32 +62819,17 @@ "/v1/responses" ], "supports_native_streaming": true, - "supports_system_messages": true - }, - "tokenlab/qwen3-livetranslate-flash-realtime": { - "input_cost_per_token": 9.4117647e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 49152, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 9.4117647e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_vision": true }, "tokenlab/qwen3-omni-flash": { - "input_cost_per_token": 2.6470589e-07, + "input_cost_per_token": 4.3e-07, "litellm_provider": "tokenlab", "max_input_tokens": 49152, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1.01470589e-06, + "output_cost_per_token": 1.66e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63521,24 +62846,8 @@ "supports_system_messages": true, "supports_vision": true }, - "tokenlab/qwen3-omni-flash-realtime": { - "input_cost_per_token": 3.2352941e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 49152, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.22058824e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true - }, "tokenlab/qwen3-vl-embedding": { - "input_cost_per_token": 1.0294118e-07, + "input_cost_per_token": 1.02941176471e-07, "litellm_provider": "tokenlab", "max_input_tokens": 32000, "max_tokens": 32000, @@ -63551,15 +62860,15 @@ "supports_vision": true }, "tokenlab/qwen3-vl-plus": { - "cache_creation_input_token_cost": 1.8382353e-07, - "cache_read_input_token_cost": 2.941177e-08, - "input_cost_per_token": 1.4705882e-07, + "cache_creation_input_token_cost": 2.5e-07, + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, "litellm_provider": "tokenlab", "max_input_tokens": 260096, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.47058824e-06, + "output_cost_per_token": 1.6e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63578,13 +62887,13 @@ "supports_vision": true }, "tokenlab/qwen3.5-27b": { - "input_cost_per_token": 8.82353e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "tokenlab", "max_input_tokens": 260096, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 7.0588236e-07, + "output_cost_per_token": 2.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63594,15 +62903,15 @@ "supports_system_messages": true }, "tokenlab/qwen3.5-flash": { - "cache_creation_input_token_cost": 3.676471e-08, - "cache_read_input_token_cost": 2.94117e-09, - "input_cost_per_token": 2.941177e-08, + "cache_creation_input_token_cost": 1.25e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, "litellm_provider": "tokenlab", "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 4e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63626,16 +62935,17 @@ "/v1/responses" ], "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_vision": true }, "tokenlab/qwen3.5-ocr": { - "input_cost_per_token": 7.352941e-08, + "input_cost_per_token": 7.3529411765e-08, "litellm_provider": "tokenlab", "max_input_tokens": 49152, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 2.9411765e-07, + "output_cost_per_token": 2.94117647059e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63653,13 +62963,13 @@ "supports_vision": true }, "tokenlab/qwen3.5-omni-flash": { - "input_cost_per_token": 2.64705882e-06, + "input_cost_per_token": 4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.05882353e-05, + "output_cost_per_token": 2.2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63677,29 +62987,32 @@ "supports_vision": true }, "tokenlab/qwen3.5-omni-flash-realtime": { - "input_cost_per_token": 3.97058824e-06, + "input_cost_per_token": 5.5e-07, "litellm_provider": "tokenlab", "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.573529412e-05, + "output_cost_per_token": 3.3e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/qwen3.5-omni-plus": { - "input_cost_per_token": 7.79411765e-06, + "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 3.132352941e-05, + "output_cost_per_token": 8.3e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63717,31 +63030,34 @@ "supports_vision": true }, "tokenlab/qwen3.5-omni-plus-realtime": { - "input_cost_per_token": 1.176470588e-05, + "input_cost_per_token": 2.1e-06, "litellm_provider": "tokenlab", "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4.411764706e-05, + "output_cost_per_token": 1.24e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/qwen3.5-plus": { - "cache_creation_input_token_cost": 1.4705882e-07, - "cache_read_input_token_cost": 1.17647e-08, - "input_cost_per_token": 1.1764705e-07, + "cache_creation_input_token_cost": 5e-07, + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 7.0588236e-07, + "output_cost_per_token": 2.4e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63752,42 +63068,25 @@ "supports_system_messages": true }, "tokenlab/qwen3.6-27b": { - "input_cost_per_token": 4.4117647e-07, + "input_cost_per_token": 6e-07, "litellm_provider": "tokenlab", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.64705882e-06, + "output_cost_per_token": 3.6e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true - }, - "tokenlab/qwen3.6-flash": { - "cache_creation_input_token_cost": 2.2058823e-07, - "cache_read_input_token_cost": 1.764706e-08, - "input_cost_per_token": 1.7647059e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 991808, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.05882353e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "tokenlab/qwen3.6-max-preview": { - "cache_read_input_token_cost": 1.475e-07, "input_cost_per_token": 1.43264706e-06, "litellm_provider": "tokenlab", "max_input_tokens": 262144, @@ -63805,35 +63104,16 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "tokenlab/qwen3.6-plus": { - "cache_creation_input_token_cost": 3.6764706e-07, - "cache_read_input_token_cost": 2.941177e-08, - "input_cost_per_token": 2.9411765e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 991808, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.76470588e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true - }, "tokenlab/qwen3.7-max": { - "cache_creation_input_token_cost": 2.20588235e-06, - "cache_read_input_token_cost": 3.5294117e-07, - "input_cost_per_token": 1.76470588e-06, + "cache_creation_input_token_cost": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 5.29411764e-06, + "output_cost_per_token": 7.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63844,15 +63124,15 @@ "supports_system_messages": true }, "tokenlab/qwen3.7-plus": { - "cache_creation_input_token_cost": 3.6764706e-07, - "cache_read_input_token_cost": 5.882353e-08, - "input_cost_per_token": 2.9411765e-07, + "cache_creation_input_token_cost": 5e-07, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, "litellm_provider": "tokenlab", "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.17647059e-06, + "output_cost_per_token": 1.6e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63882,24 +63162,27 @@ "supports_tool_choice": true }, "tokenlab/step-3.7-flash": { - "cache_read_input_token_cost": 3.970588e-08, - "input_cost_per_token": 1.9852941e-07, + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, "litellm_provider": "tokenlab", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.19117647e-06, + "output_cost_per_token": 1.15e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], + "supports_function_calling": true, "supports_native_streaming": true, - "supports_system_messages": true + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true }, "tokenlab/text-embedding-3-large": { - "input_cost_per_token": 1.3e-07, + "input_cost_per_token": 9.1e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8191, "max_tokens": 8191, @@ -63911,7 +63194,7 @@ ] }, "tokenlab/text-embedding-3-small": { - "input_cost_per_token": 2e-08, + "input_cost_per_token": 1.4e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8191, "max_tokens": 8191, @@ -63935,7 +63218,7 @@ ] }, "tokenlab/text-embedding-v4": { - "input_cost_per_token": 7.352941e-08, + "input_cost_per_token": 7e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_tokens": 8192, @@ -63947,13 +63230,13 @@ ] }, "tokenlab/tongyi-intent-detect-v3": { - "input_cost_per_token": 5.882353e-08, + "input_cost_per_token": 5.8823529412e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.4705882e-07, + "output_cost_per_token": 1.47058823529e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63963,13 +63246,13 @@ "supports_system_messages": true }, "tokenlab/tongyi-xiaomi-analysis-flash": { - "input_cost_per_token": 2.941177e-08, + "input_cost_per_token": 2.9411764705e-08, "litellm_provider": "tokenlab", "max_input_tokens": 28672, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 5.882353e-08, + "output_cost_per_token": 5.8823529412e-08, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -63979,13 +63262,13 @@ "supports_system_messages": true }, "tokenlab/tongyi-xiaomi-analysis-pro": { - "input_cost_per_token": 1.4705882e-07, + "input_cost_per_token": 1.47058823529e-07, "litellm_provider": "tokenlab", "max_input_tokens": 28672, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.9705883e-07, + "output_cost_per_token": 3.97058823529e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", diff --git a/tests/unit/llms/openai_like/test_tokenlab_provider.py b/tests/unit/llms/openai_like/test_tokenlab_provider.py index b459f9ba119..55348399306 100644 --- a/tests/unit/llms/openai_like/test_tokenlab_provider.py +++ b/tests/unit/llms/openai_like/test_tokenlab_provider.py @@ -163,8 +163,11 @@ class TestTokenLabCostMap: prompt_tokens=1_000_000, completion_tokens=1_000_000, ) - assert prompt_cost == pytest.approx(1.5) - assert completion_cost == pytest.approx(9.0) + assert prompt_cost == pytest.approx(litellm.model_cost["tokenlab/gpt-5.5"]["input_cost_per_token"] * 1_000_000) + assert completion_cost == pytest.approx( + litellm.model_cost["tokenlab/gpt-5.5"]["output_cost_per_token"] * 1_000_000 + ) + assert prompt_cost > 0 and completion_cost > 0 def test_embedding_cost_is_wired(self): prompt_cost, completion_cost = litellm.cost_per_token( @@ -172,5 +175,8 @@ class TestTokenLabCostMap: prompt_tokens=1_000_000, completion_tokens=0, ) - assert prompt_cost == pytest.approx(0.02) + assert prompt_cost == pytest.approx( + litellm.model_cost["tokenlab/text-embedding-3-small"]["input_cost_per_token"] * 1_000_000 + ) + assert prompt_cost > 0 assert completion_cost == 0 From 738ae356493f0af1ba6770846bc64f9abb508662 Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Tue, 6 Oct 2026 23:11:33 +0800 Subject: [PATCH 09/13] fix(tokenlab): resync the model cost entries with the current catalog TokenLab removed 9 models from its public catalog after the last sync: gemini-2.5-pro, gpt-5-pro, gpt-5-search-api, kimi-k2.5, qwen3-livetranslate-flash, qwen3.5-livetranslate-flash-realtime, qwen3.5-omni-flash-realtime, qwen3.5-omni-plus-realtime and qwen3.6-max-preview. Their entries are gone. The catalog also changed some values: - claude-sonnet-5: prices and cache prices are now 0.6 / 3 per 1M. - claude-sonnet-4-6: limits are now 1M input and 128k output tokens. - qwen-doc-turbo, qwen3.5-ocr, qwen3-vl-embedding and tongyi-intent-detect-v3: prices follow the rounded catalog values. - supports_response_schema follows the catalog json-mode tag: removed from doubao-seed-2.1-pro and doubao-seed-evolving, added to kimi-k2.6 and step-3.7-flash. Values come from https://tokenlab.sh/api/public/model-data/models (registry revision 455), which agrees with https://api.tokenlab.sh/v1/models for every kept entry. Co-Authored-By: Claude Opus 5.5 --- ...odel_prices_and_context_window_backup.json | 233 ++---------------- model_prices_and_context_window.json | 233 ++---------------- 2 files changed, 36 insertions(+), 430 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 6a057fe8be1..73229159bbe 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -60971,9 +60971,9 @@ "cache_read_input_token_cost": 9e-08, "input_cost_per_token": 9e-07, "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://api.tokenlab.sh/v1/models", @@ -60998,15 +60998,15 @@ "supports_vision": true }, "tokenlab/claude-sonnet-5": { - "cache_creation_input_token_cost": 1.125e-06, - "cache_read_input_token_cost": 9e-08, - "input_cost_per_token": 9e-07, + "cache_creation_input_token_cost": 7.5e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 3e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61214,7 +61214,6 @@ "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -61305,36 +61304,6 @@ "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/gemini-2.5-pro": { - "cache_read_input_token_cost": 6.25e-08, - "input_cost_per_token": 6.25e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -61716,63 +61685,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/gpt-5-pro": { - "input_cost_per_token": 1.5e-05, - "litellm_provider": "tokenlab", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00012, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/gpt-5-search-api": { - "cache_read_input_token_cost": 1e-06, - "input_cost_per_token": 2e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/gpt-5.1": { "cache_read_input_token_cost": 8.75e-08, "input_cost_per_token": 8.75e-07, @@ -62284,27 +62196,6 @@ "supports_native_streaming": true, "supports_system_messages": true }, - "tokenlab/kimi-k2.5": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, @@ -62322,6 +62213,7 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -62606,15 +62498,15 @@ "supports_vision": true }, "tokenlab/qwen-doc-turbo": { - "cache_creation_input_token_cost": 1.10294117647e-07, - "cache_read_input_token_cost": 1.7647058824e-08, - "input_cost_per_token": 8.8235294117e-08, + "cache_creation_input_token_cost": 1.0875e-07, + "cache_read_input_token_cost": 1.74e-08, + "input_cost_per_token": 8.7e-08, "litellm_provider": "tokenlab", "max_input_tokens": 253952, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.47058823529e-07, + "output_cost_per_token": 1.44e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62805,23 +62697,6 @@ "supports_prompt_caching": true, "supports_system_messages": true }, - "tokenlab/qwen3-livetranslate-flash": { - "input_cost_per_token": 1.47058824e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 49152, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.47058824e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_vision": true - }, "tokenlab/qwen3-omni-flash": { "input_cost_per_token": 4.3e-07, "litellm_provider": "tokenlab", @@ -62847,7 +62722,7 @@ "supports_vision": true }, "tokenlab/qwen3-vl-embedding": { - "input_cost_per_token": 1.02941176471e-07, + "input_cost_per_token": 1e-07, "litellm_provider": "tokenlab", "max_input_tokens": 32000, "max_tokens": 32000, @@ -62921,31 +62796,14 @@ "supports_prompt_caching": true, "supports_system_messages": true }, - "tokenlab/qwen3.5-livetranslate-flash-realtime": { - "input_cost_per_token": 5.88235294e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 49152, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.470588236e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_vision": true - }, "tokenlab/qwen3.5-ocr": { - "input_cost_per_token": 7.3529411765e-08, + "input_cost_per_token": 6.9e-08, "litellm_provider": "tokenlab", "max_input_tokens": 49152, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 2.94117647059e-07, + "output_cost_per_token": 2.75e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62986,25 +62844,6 @@ "supports_system_messages": true, "supports_vision": true }, - "tokenlab/qwen3.5-omni-flash-realtime": { - "input_cost_per_token": 5.5e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 196608, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3.3e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/qwen3.5-omni-plus": { "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", @@ -63029,25 +62868,6 @@ "supports_system_messages": true, "supports_vision": true }, - "tokenlab/qwen3.5-omni-plus-realtime": { - "input_cost_per_token": 2.1e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 196608, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.24e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/qwen3.5-plus": { "cache_creation_input_token_cost": 5e-07, "cache_read_input_token_cost": 4e-08, @@ -63086,24 +62906,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/qwen3.6-max-preview": { - "input_cost_per_token": 1.43264706e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 8.59632353e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/qwen3.7-max": { "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, @@ -63178,6 +62980,7 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, @@ -63230,13 +63033,13 @@ ] }, "tokenlab/tongyi-intent-detect-v3": { - "input_cost_per_token": 5.8823529412e-08, + "input_cost_per_token": 5.8e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.47058823529e-07, + "output_cost_per_token": 1.44e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6a057fe8be1..73229159bbe 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -60971,9 +60971,9 @@ "cache_read_input_token_cost": 9e-08, "input_cost_per_token": 9e-07, "litellm_provider": "tokenlab", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://api.tokenlab.sh/v1/models", @@ -60998,15 +60998,15 @@ "supports_vision": true }, "tokenlab/claude-sonnet-5": { - "cache_creation_input_token_cost": 1.125e-06, - "cache_read_input_token_cost": 9e-08, - "input_cost_per_token": 9e-07, + "cache_creation_input_token_cost": 7.5e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4.5e-06, + "output_cost_per_token": 3e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -61214,7 +61214,6 @@ "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -61305,36 +61304,6 @@ "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/gemini-2.5-pro": { - "cache_read_input_token_cost": 6.25e-08, - "input_cost_per_token": 6.25e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -61716,63 +61685,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/gpt-5-pro": { - "input_cost_per_token": 1.5e-05, - "litellm_provider": "tokenlab", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00012, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "tokenlab/gpt-5-search-api": { - "cache_read_input_token_cost": 1e-06, - "input_cost_per_token": 2e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/gpt-5.1": { "cache_read_input_token_cost": 8.75e-08, "input_cost_per_token": 8.75e-07, @@ -62284,27 +62196,6 @@ "supports_native_streaming": true, "supports_system_messages": true }, - "tokenlab/kimi-k2.5": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, @@ -62322,6 +62213,7 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -62606,15 +62498,15 @@ "supports_vision": true }, "tokenlab/qwen-doc-turbo": { - "cache_creation_input_token_cost": 1.10294117647e-07, - "cache_read_input_token_cost": 1.7647058824e-08, - "input_cost_per_token": 8.8235294117e-08, + "cache_creation_input_token_cost": 1.0875e-07, + "cache_read_input_token_cost": 1.74e-08, + "input_cost_per_token": 8.7e-08, "litellm_provider": "tokenlab", "max_input_tokens": 253952, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.47058823529e-07, + "output_cost_per_token": 1.44e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62805,23 +62697,6 @@ "supports_prompt_caching": true, "supports_system_messages": true }, - "tokenlab/qwen3-livetranslate-flash": { - "input_cost_per_token": 1.47058824e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 49152, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.47058824e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_vision": true - }, "tokenlab/qwen3-omni-flash": { "input_cost_per_token": 4.3e-07, "litellm_provider": "tokenlab", @@ -62847,7 +62722,7 @@ "supports_vision": true }, "tokenlab/qwen3-vl-embedding": { - "input_cost_per_token": 1.02941176471e-07, + "input_cost_per_token": 1e-07, "litellm_provider": "tokenlab", "max_input_tokens": 32000, "max_tokens": 32000, @@ -62921,31 +62796,14 @@ "supports_prompt_caching": true, "supports_system_messages": true }, - "tokenlab/qwen3.5-livetranslate-flash-realtime": { - "input_cost_per_token": 5.88235294e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 49152, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.470588236e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_vision": true - }, "tokenlab/qwen3.5-ocr": { - "input_cost_per_token": 7.3529411765e-08, + "input_cost_per_token": 6.9e-08, "litellm_provider": "tokenlab", "max_input_tokens": 49152, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 2.94117647059e-07, + "output_cost_per_token": 2.75e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62986,25 +62844,6 @@ "supports_system_messages": true, "supports_vision": true }, - "tokenlab/qwen3.5-omni-flash-realtime": { - "input_cost_per_token": 5.5e-07, - "litellm_provider": "tokenlab", - "max_input_tokens": 196608, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3.3e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/qwen3.5-omni-plus": { "input_cost_per_token": 1.4e-06, "litellm_provider": "tokenlab", @@ -63029,25 +62868,6 @@ "supports_system_messages": true, "supports_vision": true }, - "tokenlab/qwen3.5-omni-plus-realtime": { - "input_cost_per_token": 2.1e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 196608, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.24e-05, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "tokenlab/qwen3.5-plus": { "cache_creation_input_token_cost": 5e-07, "cache_read_input_token_cost": 4e-08, @@ -63086,24 +62906,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "tokenlab/qwen3.6-max-preview": { - "input_cost_per_token": 1.43264706e-06, - "litellm_provider": "tokenlab", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 8.59632353e-06, - "source": "https://api.tokenlab.sh/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "tokenlab/qwen3.7-max": { "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, @@ -63178,6 +62980,7 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, @@ -63230,13 +63033,13 @@ ] }, "tokenlab/tongyi-intent-detect-v3": { - "input_cost_per_token": 5.8823529412e-08, + "input_cost_per_token": 5.8e-08, "litellm_provider": "tokenlab", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.47058823529e-07, + "output_cost_per_token": 1.44e-07, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", From e6d9654f811b9a3c0fde240d942f3a45b57574e1 Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Tue, 6 Oct 2026 23:39:09 +0800 Subject: [PATCH 10/13] feat(tokenlab): add the remaining per-token chat and embedding models Add 55 TokenLab entries: every per-token chat and embedding model in the public catalog (registry revision 455) that the cost map did not list yet. The entries use the same rules as the existing rows: platform prices and cache prices, catalog token limits, and capability flags from the catalog tags. - gpt-5.6-luna/sol/terra, gpt-6-astra/luna/sol and gpt-6.1-sol get the *_above_272k_tokens prices from the catalog context tier. - grok-4.5, grok-4.6 and grok-4.7 get the *_above_200k_tokens prices. - Claude models that reject manual thinking get supports_adaptive_thinking and supports_sampling_params: false, as the existing Claude rows do. - qwen3.8-omni-flash has no output limit and tongyi-embedding-vision-plus has no input limit in the catalog, so these entries leave out the limit fields. 11 catalog models are not added because their catalog tags and capability fields disagree: codestral-embed, deepseek-v4.1-flash, ember-1, laguna-s-2.1, ling-3.0-flash-vl, mercury-2.5, mimo-v2.6-flash, mimo-v2.6-pro, mistral-medium-3.5, nova-2-lite and solar-pro4. Co-Authored-By: Claude Opus 5.5 --- ...odel_prices_and_context_window_backup.json | 1318 +++++++++++++++++ model_prices_and_context_window.json | 1318 +++++++++++++++++ 2 files changed, 2636 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 73229159bbe..931d4bdeabf 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -60838,6 +60838,39 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/claude-fable-5-1": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_adaptive_thinking": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/claude-haiku-4-5": { "cache_creation_input_token_cost": 3.75e-07, "cache_read_input_token_cost": 3e-08, @@ -60966,6 +60999,72 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/claude-opus-5": { + "cache_creation_input_token_cost": 1.875e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_adaptive_thinking": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-opus-5-5": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_adaptive_thinking": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/claude-sonnet-4-6": { "cache_creation_input_token_cost": 1.125e-06, "cache_read_input_token_cost": 9e-08, @@ -61030,6 +61129,39 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/claude-sonnet-5-5": { + "cache_creation_input_token_cost": 7.5e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_adaptive_thinking": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/deepseek-v4-flash": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, @@ -61051,6 +61183,35 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/deepseek-v4-pro": { "cache_creation_input_token_cost": 6.6e-07, "cache_read_input_token_cost": 2.2e-08, @@ -61189,6 +61350,35 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/doubao-seed-2.1-lite": { + "cache_read_input_token_cost": 2.3529411765e-08, + "input_cost_per_token": 1.17647058824e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.97058823529e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/doubao-seed-2.1-pro": { "cache_read_input_token_cost": 1.7647059e-07, "input_cost_per_token": 8.8235294e-07, @@ -61308,6 +61498,95 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/gemini-2.5-flash": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3-flash-preview": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/gemini-3.1-flash-lite": { "cache_read_input_token_cost": 1.25e-08, "input_cost_per_token": 1.25e-07, @@ -61395,6 +61674,146 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/gemini-3.5-flash-lite": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.6-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.7-flash": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.8-flash": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-embedding-001": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/gemini-embedding-2": { + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "tokenlab/glm-5": { "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 2e-07, @@ -61479,6 +61898,86 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/glm-5.3": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/glm-5.3-flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/glm-5.3-flashx": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3.7e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/glm-5v-turbo": { "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 1.2e-06, @@ -61508,6 +62007,35 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/gpt-4.1": { + "cache_read_input_token_cost": 3.5e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5.6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/gpt-4.1-mini": { "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 2.8e-07, @@ -61974,6 +62502,242 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/gpt-5.6-luna": { + "cache_creation_input_token_cost": 7.5e-08, + "cache_creation_input_token_cost_above_272k_tokens": 1.5e-07, + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-08, + "input_cost_per_token": 6e-08, + "input_cost_per_token_above_272k_tokens": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "output_cost_per_token_above_272k_tokens": 5.4e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.6-sol": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.6-terra": { + "cache_creation_input_token_cost": 7.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 1.5e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 6e-07, + "input_cost_per_token_above_272k_tokens": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "output_cost_per_token_above_272k_tokens": 5.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-6-astra": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 7.5e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_272k_tokens": 6e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_272k_tokens": 6e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-6-luna": { + "cache_creation_input_token_cost": 3.75e-08, + "cache_creation_input_token_cost_above_272k_tokens": 7.5e-08, + "cache_read_input_token_cost": 3e-09, + "cache_read_input_token_cost_above_272k_tokens": 6e-09, + "input_cost_per_token": 3e-08, + "input_cost_per_token_above_272k_tokens": 6e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "output_cost_per_token_above_272k_tokens": 2.25e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-6-sol": { + "cache_creation_input_token_cost": 7.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 1.5e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 6e-07, + "input_cost_per_token_above_272k_tokens": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_272k_tokens": 4.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-6.1-sol": { + "cache_creation_input_token_cost": 7.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 1.5e-06, + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_above_272k_tokens": 6e-08, + "input_cost_per_token": 6e-07, + "input_cost_per_token_above_272k_tokens": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_272k_tokens": 4.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/gpt-oss-120b": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, @@ -62134,6 +62898,104 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/grok-4.5": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_above_200k_tokens": 3e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 500000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_200k_tokens": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.6": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens": 5e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 500000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_200k_tokens": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.7": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens": 5e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 500000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_200k_tokens": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/grok-build-0.1": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, @@ -62196,6 +63058,49 @@ "supports_native_streaming": true, "supports_system_messages": true }, + "tokenlab/hy3": { + "cache_read_input_token_cost": 3.3e-08, + "input_cost_per_token": 1.32e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.28e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/hy4-preview": { + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 8.34e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 960000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.501e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, @@ -62276,6 +63181,66 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/kimi-k2.8-preview": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/kimi-k3": { + "cache_creation_input_token_cost": 3e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/mimo-v2.5": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-09, @@ -62466,6 +63431,18 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/mistral-embed": { + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "tokenlab/o3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 3.5e-07, @@ -62497,6 +63474,30 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/pplx-embed-v1-0.6b": { + "input_cost_per_token": 4e-09, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/pplx-embed-v1-4b": { + "input_cost_per_token": 3e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "tokenlab/qwen-doc-turbo": { "cache_creation_input_token_cost": 1.0875e-07, "cache_read_input_token_cost": 1.74e-08, @@ -62944,6 +63945,163 @@ "supports_prompt_caching": true, "supports_system_messages": true }, + "tokenlab/qwen3.7-text-embedding": { + "input_cost_per_token": 7.3529411765e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/qwen3.7-text-embedding-flash": { + "input_cost_per_token": 1.8382352941e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/qwen3.8-2.4t-a95b": { + "input_cost_per_token": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/qwen3.8-27b": { + "cache_creation_input_token_cost": 6.25e-07, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/qwen3.8-flash": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/qwen3.8-max": { + "input_cost_per_token": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/step-3.5-flash": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 1e-07, @@ -62984,6 +64142,35 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/step-5-preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.7e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/text-embedding-3-large": { "input_cost_per_token": 9.1e-08, "litellm_provider": "tokenlab", @@ -63032,6 +64219,17 @@ "/v1/embeddings" ] }, + "tokenlab/tongyi-embedding-vision-plus": { + "input_cost_per_token": 9e-08, + "litellm_provider": "tokenlab", + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supports_vision": true + }, "tokenlab/tongyi-intent-detect-v3": { "input_cost_per_token": 5.8e-08, "litellm_provider": "tokenlab", @@ -63080,6 +64278,126 @@ "supports_native_streaming": true, "supports_system_messages": true }, + "tokenlab/voyage-3-large": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-3.5": { + "input_cost_per_token": 6e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-3.5-lite": { + "input_cost_per_token": 2e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-4": { + "input_cost_per_token": 6e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-4-large": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-4-lite": { + "input_cost_per_token": 2e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-code-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-code-3": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-finance-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-law-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "fallback_generalizations": { "rules": [ { diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 73229159bbe..931d4bdeabf 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -60838,6 +60838,39 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/claude-fable-5-1": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_adaptive_thinking": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/claude-haiku-4-5": { "cache_creation_input_token_cost": 3.75e-07, "cache_read_input_token_cost": 3e-08, @@ -60966,6 +60999,72 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/claude-opus-5": { + "cache_creation_input_token_cost": 1.875e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_adaptive_thinking": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/claude-opus-5-5": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_adaptive_thinking": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/claude-sonnet-4-6": { "cache_creation_input_token_cost": 1.125e-06, "cache_read_input_token_cost": 9e-08, @@ -61030,6 +61129,39 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/claude-sonnet-5-5": { + "cache_creation_input_token_cost": 7.5e-07, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_adaptive_thinking": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/deepseek-v4-flash": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, @@ -61051,6 +61183,35 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/deepseek-v4-pro": { "cache_creation_input_token_cost": 6.6e-07, "cache_read_input_token_cost": 2.2e-08, @@ -61189,6 +61350,35 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/doubao-seed-2.1-lite": { + "cache_read_input_token_cost": 2.3529411765e-08, + "input_cost_per_token": 1.17647058824e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.97058823529e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/doubao-seed-2.1-pro": { "cache_read_input_token_cost": 1.7647059e-07, "input_cost_per_token": 8.8235294e-07, @@ -61308,6 +61498,95 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/gemini-2.5-flash": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3-flash-preview": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/gemini-3.1-flash-lite": { "cache_read_input_token_cost": 1.25e-08, "input_cost_per_token": 1.25e-07, @@ -61395,6 +61674,146 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/gemini-3.5-flash-lite": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.6-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.7-flash": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-3.8-flash": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gemini-embedding-001": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/gemini-embedding-2": { + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "tokenlab/glm-5": { "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 2e-07, @@ -61479,6 +61898,86 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/glm-5.3": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/glm-5.3-flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/glm-5.3-flashx": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3.7e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/glm-5v-turbo": { "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 1.2e-06, @@ -61508,6 +62007,35 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/gpt-4.1": { + "cache_read_input_token_cost": 3.5e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5.6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/gpt-4.1-mini": { "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 2.8e-07, @@ -61974,6 +62502,242 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/gpt-5.6-luna": { + "cache_creation_input_token_cost": 7.5e-08, + "cache_creation_input_token_cost_above_272k_tokens": 1.5e-07, + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-08, + "input_cost_per_token": 6e-08, + "input_cost_per_token_above_272k_tokens": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "output_cost_per_token_above_272k_tokens": 5.4e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.6-sol": { + "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 3e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_above_272k_tokens": 2.4e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-5.6-terra": { + "cache_creation_input_token_cost": 7.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 1.5e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 6e-07, + "input_cost_per_token_above_272k_tokens": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "output_cost_per_token_above_272k_tokens": 5.4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-6-astra": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 7.5e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_272k_tokens": 6e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_272k_tokens": 6e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-6-luna": { + "cache_creation_input_token_cost": 3.75e-08, + "cache_creation_input_token_cost_above_272k_tokens": 7.5e-08, + "cache_read_input_token_cost": 3e-09, + "cache_read_input_token_cost_above_272k_tokens": 6e-09, + "input_cost_per_token": 3e-08, + "input_cost_per_token_above_272k_tokens": 6e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "output_cost_per_token_above_272k_tokens": 2.25e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-6-sol": { + "cache_creation_input_token_cost": 7.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 1.5e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, + "input_cost_per_token": 6e-07, + "input_cost_per_token_above_272k_tokens": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_272k_tokens": 4.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/gpt-6.1-sol": { + "cache_creation_input_token_cost": 7.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 1.5e-06, + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_above_272k_tokens": 6e-08, + "input_cost_per_token": 6e-07, + "input_cost_per_token_above_272k_tokens": 1.2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_272k_tokens": 4.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/gpt-oss-120b": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, @@ -62134,6 +62898,104 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/grok-4.5": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_above_200k_tokens": 3e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 500000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_200k_tokens": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.6": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens": 5e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 500000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_200k_tokens": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/grok-4.7": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens": 5e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 500000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_200k_tokens": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/grok-build-0.1": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, @@ -62196,6 +63058,49 @@ "supports_native_streaming": true, "supports_system_messages": true }, + "tokenlab/hy3": { + "cache_read_input_token_cost": 3.3e-08, + "input_cost_per_token": 1.32e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 196608, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.28e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/hy4-preview": { + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 8.34e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 960000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.501e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, @@ -62276,6 +63181,66 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/kimi-k2.8-preview": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/kimi-k3": { + "cache_creation_input_token_cost": 3e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/mimo-v2.5": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-09, @@ -62466,6 +63431,18 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/mistral-embed": { + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "tokenlab/o3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 3.5e-07, @@ -62497,6 +63474,30 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/pplx-embed-v1-0.6b": { + "input_cost_per_token": 4e-09, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/pplx-embed-v1-4b": { + "input_cost_per_token": 3e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "tokenlab/qwen-doc-turbo": { "cache_creation_input_token_cost": 1.0875e-07, "cache_read_input_token_cost": 1.74e-08, @@ -62944,6 +63945,163 @@ "supports_prompt_caching": true, "supports_system_messages": true }, + "tokenlab/qwen3.7-text-embedding": { + "input_cost_per_token": 7.3529411765e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/qwen3.7-text-embedding-flash": { + "input_cost_per_token": 1.8382352941e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/qwen3.8-2.4t-a95b": { + "input_cost_per_token": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/qwen3.8-27b": { + "cache_creation_input_token_cost": 6.25e-07, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/qwen3.8-flash": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/qwen3.8-max": { + "input_cost_per_token": 2e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/step-3.5-flash": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 1e-07, @@ -62984,6 +64142,35 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/step-5-preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.7e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/text-embedding-3-large": { "input_cost_per_token": 9.1e-08, "litellm_provider": "tokenlab", @@ -63032,6 +64219,17 @@ "/v1/embeddings" ] }, + "tokenlab/tongyi-embedding-vision-plus": { + "input_cost_per_token": 9e-08, + "litellm_provider": "tokenlab", + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supports_vision": true + }, "tokenlab/tongyi-intent-detect-v3": { "input_cost_per_token": 5.8e-08, "litellm_provider": "tokenlab", @@ -63080,6 +64278,126 @@ "supports_native_streaming": true, "supports_system_messages": true }, + "tokenlab/voyage-3-large": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-3.5": { + "input_cost_per_token": 6e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-3.5-lite": { + "input_cost_per_token": 2e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-4": { + "input_cost_per_token": 6e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-4-large": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-4-lite": { + "input_cost_per_token": 2e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-code-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-code-3": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-finance-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, + "tokenlab/voyage-law-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "fallback_generalizations": { "rules": [ { From f729fd893953c37310bdb65623a1f677ed0f2967 Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Tue, 6 Oct 2026 23:44:45 +0800 Subject: [PATCH 11/13] fix(tokenlab): add the context-tier prices to the existing entries Nine TokenLab entries charged the base price at every prompt length, but the catalog prices long prompts higher. They now carry the long-context prices from the catalog (registry revision 456), with the same fields LiteLLM uses for OpenAI, xAI and Gemini: - gpt-5.4, gpt-5.5, gpt-5.5-pro: *_above_272k_tokens - grok-4.20, grok-4.20-multi-agent, grok-4.20-non-reasoning, grok-4.3, grok-build-0.1, gemini-3.1-pro-preview: *_above_200k_tokens test_chat_cost_is_wired used a 1M-token prompt, which is now in the long-context tier. It now uses a 100K-token prompt, and a new test checks that a 300K-token prompt uses the *_above_272k_tokens prices. Co-Authored-By: Claude Opus 5.5 --- ...odel_prices_and_context_window_backup.json | 26 +++++++++++++++++++ model_prices_and_context_window.json | 26 +++++++++++++++++++ .../openai_like/test_tokenlab_provider.py | 26 ++++++++++++++++--- 3 files changed, 74 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 931d4bdeabf..ddcfb8bb034 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -61618,13 +61618,16 @@ }, "tokenlab/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 9e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62332,13 +62335,16 @@ }, "tokenlab/gpt-5.4": { "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 3.5e-07, "input_cost_per_token": 1.75e-06, + "input_cost_per_token_above_272k_tokens": 3.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_272k_tokens": 1.575e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62446,13 +62452,16 @@ }, "tokenlab/gpt-5.5": { "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 3e-07, "input_cost_per_token": 1.5e-06, + "input_cost_per_token_above_272k_tokens": 3e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-06, + "output_cost_per_token_above_272k_tokens": 1.35e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62476,12 +62485,14 @@ }, "tokenlab/gpt-5.5-pro": { "input_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, "litellm_provider": "tokenlab", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00018, + "output_cost_per_token_above_272k_tokens": 0.00027, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62781,13 +62792,16 @@ }, "tokenlab/grok-4.20": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 6.25e-07, + "input_cost_per_token_above_200k_tokens": 1.25e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_200k_tokens": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62811,13 +62825,16 @@ }, "tokenlab/grok-4.20-multi-agent": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 6.25e-07, + "input_cost_per_token_above_200k_tokens": 1.25e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_200k_tokens": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62841,13 +62858,16 @@ }, "tokenlab/grok-4.20-non-reasoning": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 6.25e-07, + "input_cost_per_token_above_200k_tokens": 1.25e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_200k_tokens": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62870,13 +62890,16 @@ }, "tokenlab/grok-4.3": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 6.25e-07, + "input_cost_per_token_above_200k_tokens": 1.25e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_200k_tokens": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62998,13 +63021,16 @@ }, "tokenlab/grok-build-0.1": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 5e-07, + "input_cost_per_token_above_200k_tokens": 1e-06, "litellm_provider": "tokenlab", "max_input_tokens": 256000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-06, + "output_cost_per_token_above_200k_tokens": 2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 931d4bdeabf..ddcfb8bb034 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -61618,13 +61618,16 @@ }, "tokenlab/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 9e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62332,13 +62335,16 @@ }, "tokenlab/gpt-5.4": { "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 3.5e-07, "input_cost_per_token": 1.75e-06, + "input_cost_per_token_above_272k_tokens": 3.5e-06, "litellm_provider": "tokenlab", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_272k_tokens": 1.575e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62446,13 +62452,16 @@ }, "tokenlab/gpt-5.5": { "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 3e-07, "input_cost_per_token": 1.5e-06, + "input_cost_per_token_above_272k_tokens": 3e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-06, + "output_cost_per_token_above_272k_tokens": 1.35e-05, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62476,12 +62485,14 @@ }, "tokenlab/gpt-5.5-pro": { "input_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, "litellm_provider": "tokenlab", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00018, + "output_cost_per_token_above_272k_tokens": 0.00027, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62781,13 +62792,16 @@ }, "tokenlab/grok-4.20": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 6.25e-07, + "input_cost_per_token_above_200k_tokens": 1.25e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_200k_tokens": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62811,13 +62825,16 @@ }, "tokenlab/grok-4.20-multi-agent": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 6.25e-07, + "input_cost_per_token_above_200k_tokens": 1.25e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_200k_tokens": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62841,13 +62858,16 @@ }, "tokenlab/grok-4.20-non-reasoning": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 6.25e-07, + "input_cost_per_token_above_200k_tokens": 1.25e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_200k_tokens": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62870,13 +62890,16 @@ }, "tokenlab/grok-4.3": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 6.25e-07, + "input_cost_per_token_above_200k_tokens": 1.25e-06, "litellm_provider": "tokenlab", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_200k_tokens": 2.5e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", @@ -62998,13 +63021,16 @@ }, "tokenlab/grok-build-0.1": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_200k_tokens": 2e-07, "input_cost_per_token": 5e-07, + "input_cost_per_token_above_200k_tokens": 1e-06, "litellm_provider": "tokenlab", "max_input_tokens": 256000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-06, + "output_cost_per_token_above_200k_tokens": 2e-06, "source": "https://api.tokenlab.sh/v1/models", "supported_endpoints": [ "/v1/chat/completions", diff --git a/tests/unit/llms/openai_like/test_tokenlab_provider.py b/tests/unit/llms/openai_like/test_tokenlab_provider.py index 55348399306..2f5cb7bc3da 100644 --- a/tests/unit/llms/openai_like/test_tokenlab_provider.py +++ b/tests/unit/llms/openai_like/test_tokenlab_provider.py @@ -160,15 +160,33 @@ class TestTokenLabCostMap: def test_chat_cost_is_wired(self): prompt_cost, completion_cost = litellm.cost_per_token( model="tokenlab/gpt-5.5", - prompt_tokens=1_000_000, - completion_tokens=1_000_000, + prompt_tokens=100_000, + completion_tokens=100_000, ) - assert prompt_cost == pytest.approx(litellm.model_cost["tokenlab/gpt-5.5"]["input_cost_per_token"] * 1_000_000) + assert prompt_cost == pytest.approx(litellm.model_cost["tokenlab/gpt-5.5"]["input_cost_per_token"] * 100_000) assert completion_cost == pytest.approx( - litellm.model_cost["tokenlab/gpt-5.5"]["output_cost_per_token"] * 1_000_000 + litellm.model_cost["tokenlab/gpt-5.5"]["output_cost_per_token"] * 100_000 ) assert prompt_cost > 0 and completion_cost > 0 + def test_chat_cost_uses_the_long_context_tier(self): + assert ( + litellm.model_cost["tokenlab/gpt-5.5"]["input_cost_per_token_above_272k_tokens"] + > litellm.model_cost["tokenlab/gpt-5.5"]["input_cost_per_token"] + ) + + prompt_cost, completion_cost = litellm.cost_per_token( + model="tokenlab/gpt-5.5", + prompt_tokens=300_000, + completion_tokens=100_000, + ) + assert prompt_cost == pytest.approx( + litellm.model_cost["tokenlab/gpt-5.5"]["input_cost_per_token_above_272k_tokens"] * 300_000 + ) + assert completion_cost == pytest.approx( + litellm.model_cost["tokenlab/gpt-5.5"]["output_cost_per_token_above_272k_tokens"] * 100_000 + ) + def test_embedding_cost_is_wired(self): prompt_cost, completion_cost = litellm.cost_per_token( model="tokenlab/text-embedding-3-small", From 60640dc76129bf2e0644123ae24a4dd80c2e8dc1 Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Tue, 6 Oct 2026 23:45:25 +0800 Subject: [PATCH 12/13] fix(tokenlab): mark glm-5.2 as supporting response schema TokenLab's catalog now declares response schema support for glm-5.2 in both its tags and its capability fields (registry revision 456), so the entry follows the same rule as the other models. --- litellm/model_prices_and_context_window_backup.json | 1 + model_prices_and_context_window.json | 1 + 2 files changed, 2 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index ddcfb8bb034..e40d8be05f0 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -61898,6 +61898,7 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index ddcfb8bb034..e40d8be05f0 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -61898,6 +61898,7 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, From addd917894a70161c4c67e5f94a7fe9590f5dd63 Mon Sep 17 00:00:00 2001 From: hedging8563 Date: Wed, 7 Oct 2026 00:48:43 +0800 Subject: [PATCH 13/13] feat(tokenlab): add 11 models and mark prompt caching on 5 entries TokenLab fixed the catalog entries whose tags and capability fields disagreed (Registry revision 457). Each value was checked with production requests: - Add 11 models: deepseek-v4.1-flash, codestral-embed, ember-1, laguna-s-2.1, ling-3.0-flash-vl, mercury-2.5, mimo-v2.6-flash, mimo-v2.6-pro, mistral-medium-3.5, nova-2-lite, solar-pro4. - Set supports_prompt_caching on mimo-v2.5, mimo-v2.5-pro, minimax-m2.1, minimax-m2.1-highspeed and step-3.5-flash. A repeated prompt returned cached_tokens on these models. - mistral-medium-3.5, nova-2-lite and minimax-m2 keep their cache read price but do not claim prompt caching. Plain repeated prompts returned no cached tokens on them. --- ...odel_prices_and_context_window_backup.json | 247 ++++++++++++++++++ model_prices_and_context_window.json | 247 ++++++++++++++++++ 2 files changed, 494 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e40d8be05f0..511d76577b3 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -61162,6 +61162,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/codestral-embed": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "tokenlab/deepseek-v4-flash": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, @@ -61234,6 +61246,37 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/deepseek-v4.1-flash": { + "cache_creation_input_token_cost": 1.5e-07, + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/doubao-seed-2.0-code": { "cache_creation_input_token_cost": 4.7058824e-07, "cache_read_input_token_cost": 9.411765e-08, @@ -61498,6 +61541,25 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/ember-1": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/gemini-2.5-flash": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, @@ -63268,6 +63330,74 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/laguna-s-2.1": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/ling-3.0-flash-vl": { + "cache_read_input_token_cost": 4.117647059e-09, + "input_cost_per_token": 2.0588235294e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.1764705882e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mercury-2.5": { + "cache_read_input_token_cost": 4e-09, + "input_cost_per_token": 4e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 260000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/mimo-v2.5": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-09, @@ -63292,6 +63422,7 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -63313,6 +63444,63 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2.6-flash": { + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2.6-pro": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 4.35e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -63354,6 +63542,7 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -63375,6 +63564,7 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -63470,6 +63660,42 @@ "/v1/embeddings" ] }, + "tokenlab/mistral-medium-3.5": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/nova-2-lite": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/o3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 3.5e-07, @@ -64129,6 +64355,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/solar-pro4": { + "cache_read_input_token_cost": 1.8e-08, + "input_cost_per_token": 9e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 524288, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/step-3.5-flash": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 1e-07, @@ -64145,6 +64391,7 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e40d8be05f0..511d76577b3 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -61162,6 +61162,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/codestral-embed": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/embeddings" + ] + }, "tokenlab/deepseek-v4-flash": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, @@ -61234,6 +61246,37 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "tokenlab/deepseek-v4.1-flash": { + "cache_creation_input_token_cost": 1.5e-07, + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tokenlab/doubao-seed-2.0-code": { "cache_creation_input_token_cost": 4.7058824e-07, "cache_read_input_token_cost": 9.411765e-08, @@ -61498,6 +61541,25 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/ember-1": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/gemini-2.5-flash": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, @@ -63268,6 +63330,74 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/laguna-s-2.1": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/ling-3.0-flash-vl": { + "cache_read_input_token_cost": 4.117647059e-09, + "input_cost_per_token": 2.0588235294e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.1764705882e-08, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mercury-2.5": { + "cache_read_input_token_cost": 4e-09, + "input_cost_per_token": 4e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 260000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/mimo-v2.5": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-09, @@ -63292,6 +63422,7 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -63313,6 +63444,63 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2.6-flash": { + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "tokenlab/mimo-v2.6-pro": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 4.35e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true @@ -63354,6 +63542,7 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -63375,6 +63564,7 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -63470,6 +63660,42 @@ "/v1/embeddings" ] }, + "tokenlab/mistral-medium-3.5": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "tokenlab", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "tokenlab/nova-2-lite": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "tokenlab", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/o3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 3.5e-07, @@ -64129,6 +64355,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "tokenlab/solar-pro4": { + "cache_read_input_token_cost": 1.8e-08, + "input_cost_per_token": 9e-08, + "litellm_provider": "tokenlab", + "max_input_tokens": 524288, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "source": "https://api.tokenlab.sh/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "tokenlab/step-3.5-flash": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 1e-07, @@ -64145,6 +64391,7 @@ ], "supports_function_calling": true, "supports_native_streaming": true, + "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true },