diff --git a/litellm/constants.py b/litellm/constants.py index 6b984c2673c..6d1898b6626 100644 --- a/litellm/constants.py +++ b/litellm/constants.py @@ -894,6 +894,7 @@ openai_compatible_endpoints: Final[list] = [ "https://api.meta.ai/v1", "https://api.cognition.ai/v1", "https://api.scx.ai/v1", + "https://inference.gitgot.ai/v1", "https://gigachat.devices.sberbank.ru/api/v1", ] @@ -966,6 +967,7 @@ openai_compatible_providers: Final[list] = [ "meta", # Meta Model API (Muse Spark) - JSON-configured provider "cognition", "scx-ai", + "gitgot", ] openai_text_completion_compatible_providers: Final[list] = [ # providers that support `/v1/completions` "together_ai", diff --git a/litellm/llms/openai_like/providers.json b/litellm/llms/openai_like/providers.json index a458a209ea9..693e50a1155 100644 --- a/litellm/llms/openai_like/providers.json +++ b/litellm/llms/openai_like/providers.json @@ -200,5 +200,11 @@ "temperature_max": 1.99 }, "supported_endpoints": ["/v1/chat/completions"] + }, + "gitgot": { + "base_url": "https://inference.gitgot.ai/v1", + "api_key_env": "GITGOT_API_KEY", + "api_base_env": "GITGOT_API_BASE", + "supported_endpoints": ["/v1/chat/completions", "/v1/embeddings"] } } diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index aadd9bd3028..84920f9e4e1 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -65029,5 +65029,395 @@ "supports_tool_choice": false, "supports_response_schema": true, "supports_vision": false + }, + "gitgot/anthropic/claude-fable-5.1": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.0000095, + "output_cost_per_token": 0.0000475, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-haiku-4.5": { + "max_tokens": 64000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000095, + "output_cost_per_token": 0.00000475, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": false + }, + "gitgot/anthropic/claude-opus-4.5": { + "max_tokens": 64000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-opus-4.6": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-opus-4.7": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-opus-4.8": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-opus-5": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-sonnet-4.5": { + "max_tokens": 64000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.00001, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-sonnet-4.6": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.00001, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-sonnet-5": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.0000019, + "output_cost_per_token": 0.0000095, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 32768, + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0000000882, + "output_cost_per_token": 0.0000001764, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 32768, + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0000000588, + "output_cost_per_token": 0.0000001764, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 32768, + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "input_cost_per_token": 0.000001274, + "output_cost_per_token": 0.000002548, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": true + }, + "gitgot/meta-llama/Llama-3.3-70B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0000001323, + "output_cost_per_token": 0.000000392, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/moonshotai/Kimi-K2.6": { + "max_tokens": 64000, + "max_input_tokens": 262144, + "max_output_tokens": 64000, + "input_cost_per_token": 0.000000735, + "output_cost_per_token": 0.00000343, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 64000, + "max_input_tokens": 262144, + "max_output_tokens": 64000, + "input_cost_per_token": 0.0000006664, + "output_cost_per_token": 0.000003332, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5-nano": { + "max_tokens": 128000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000000475, + "output_cost_per_token": 0.00000038, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.4": { + "max_tokens": 128000, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.000002375, + "output_cost_per_token": 0.00001425, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.4-mini": { + "max_tokens": 128000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000007125, + "output_cost_per_token": 0.000004275, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.4-nano": { + "max_tokens": 128000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.00000019, + "output_cost_per_token": 0.0000011875, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.5": { + "max_tokens": 128000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.0000285, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.6-luna": { + "max_tokens": 128000, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.00000019, + "output_cost_per_token": 0.00000114, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.6-terra": { + "max_tokens": 128000, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000019, + "output_cost_per_token": 0.0000114, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": false + }, + "gitgot/openai/gpt-6-astra": { + "max_tokens": 131072, + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "input_cost_per_token": 0.0000095, + "output_cost_per_token": 0.0000475, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": false + }, + "gitgot/openai/gpt-oss-120b": { + "max_tokens": 32768, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 0.00000003626, + "output_cost_per_token": 0.0000001666, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/x-ai/grok-4.6": { + "max_tokens": 128000, + "max_input_tokens": 500000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000019, + "output_cost_per_token": 0.0000057, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false } } diff --git a/litellm/provider_endpoints_support_backup.json b/litellm/provider_endpoints_support_backup.json index dbeaccdda2d..1ac441bd34d 100644 --- a/litellm/provider_endpoints_support_backup.json +++ b/litellm/provider_endpoints_support_backup.json @@ -2065,6 +2065,23 @@ "interactions": true } }, + "gitgot": { + "display_name": "GitGot (`gitgot`)", + "url": "https://gitgot.ai/docs/quickstart", + "endpoints": { + "chat_completions": true, + "messages": false, + "responses": false, + "embeddings": true, + "image_generations": false, + "audio_transcriptions": false, + "audio_speech": false, + "moderations": false, + "batches": false, + "rerank": false, + "a2a": false + } + }, "scx-ai": { "display_name": "SCX.ai (`scx-ai`)", "url": "https://docs.litellm.ai/docs/providers/scx_ai", diff --git a/litellm/proxy/public_endpoints/provider_create_fields.json b/litellm/proxy/public_endpoints/provider_create_fields.json index cd781abee26..e9d0d667ad3 100644 --- a/litellm/proxy/public_endpoints/provider_create_fields.json +++ b/litellm/proxy/public_endpoints/provider_create_fields.json @@ -2851,6 +2851,34 @@ ], "default_model_placeholder": "sap/gpt-4" }, + { + "provider": "GITGOT", + "provider_display_name": "GitGot", + "litellm_provider": "gitgot", + "credential_fields": [ + { + "key": "api_base", + "label": "API Base", + "placeholder": "https://inference.gitgot.ai/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": "gitgot/openai/gpt-5-nano" + }, { "provider": "SCX_AI", "provider_display_name": "SCX.ai", diff --git a/litellm/types/utils.py b/litellm/types/utils.py index e3ea37dc0c8..2930718706b 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -4012,6 +4012,7 @@ class LlmProviders(str, Enum): PINSTRIPES = "pinstripes" COGNITION = "cognition" SCX_AI = "scx-ai" + GITGOT = "gitgot" DARKBLOOM = "darkbloom" META = "meta" LITELLM_AGENT = "litellm_agent" diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index aadd9bd3028..84920f9e4e1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -65029,5 +65029,395 @@ "supports_tool_choice": false, "supports_response_schema": true, "supports_vision": false + }, + "gitgot/anthropic/claude-fable-5.1": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.0000095, + "output_cost_per_token": 0.0000475, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-haiku-4.5": { + "max_tokens": 64000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000095, + "output_cost_per_token": 0.00000475, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": false + }, + "gitgot/anthropic/claude-opus-4.5": { + "max_tokens": 64000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-opus-4.6": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-opus-4.7": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-opus-4.8": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-opus-5": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.00002375, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-sonnet-4.5": { + "max_tokens": 64000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.00001, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-sonnet-4.6": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.00001, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/anthropic/claude-sonnet-5": { + "max_tokens": 64000, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.0000019, + "output_cost_per_token": 0.0000095, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, + "gitgot/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 32768, + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0000000882, + "output_cost_per_token": 0.0000001764, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 32768, + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0000000588, + "output_cost_per_token": 0.0000001764, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 32768, + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "input_cost_per_token": 0.000001274, + "output_cost_per_token": 0.000002548, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": true + }, + "gitgot/meta-llama/Llama-3.3-70B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 0.0000001323, + "output_cost_per_token": 0.000000392, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/moonshotai/Kimi-K2.6": { + "max_tokens": 64000, + "max_input_tokens": 262144, + "max_output_tokens": 64000, + "input_cost_per_token": 0.000000735, + "output_cost_per_token": 0.00000343, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 64000, + "max_input_tokens": 262144, + "max_output_tokens": 64000, + "input_cost_per_token": 0.0000006664, + "output_cost_per_token": 0.000003332, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5-nano": { + "max_tokens": 128000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000000475, + "output_cost_per_token": 0.00000038, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.4": { + "max_tokens": 128000, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.000002375, + "output_cost_per_token": 0.00001425, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.4-mini": { + "max_tokens": 128000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000007125, + "output_cost_per_token": 0.000004275, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.4-nano": { + "max_tokens": 128000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.00000019, + "output_cost_per_token": 0.0000011875, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.5": { + "max_tokens": 128000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.00000475, + "output_cost_per_token": 0.0000285, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.6-luna": { + "max_tokens": 128000, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.00000019, + "output_cost_per_token": 0.00000114, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/openai/gpt-5.6-terra": { + "max_tokens": 128000, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000019, + "output_cost_per_token": 0.0000114, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": false + }, + "gitgot/openai/gpt-6-astra": { + "max_tokens": 131072, + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "input_cost_per_token": 0.0000095, + "output_cost_per_token": 0.0000475, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": false + }, + "gitgot/openai/gpt-oss-120b": { + "max_tokens": 32768, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "input_cost_per_token": 0.00000003626, + "output_cost_per_token": 0.0000001666, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false + }, + "gitgot/x-ai/grok-4.6": { + "max_tokens": 128000, + "max_input_tokens": 500000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000019, + "output_cost_per_token": 0.0000057, + "litellm_provider": "gitgot", + "mode": "chat", + "source": "https://inference.gitgot.ai/v1/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_reasoning": false } } diff --git a/provider_endpoints_support.json b/provider_endpoints_support.json index c71f4a82a4a..5b0cb6fd7b5 100644 --- a/provider_endpoints_support.json +++ b/provider_endpoints_support.json @@ -2299,6 +2299,23 @@ "interactions": true } }, + "gitgot": { + "display_name": "GitGot (`gitgot`)", + "url": "https://gitgot.ai/docs/quickstart", + "endpoints": { + "chat_completions": true, + "messages": false, + "responses": false, + "embeddings": true, + "image_generations": false, + "audio_transcriptions": false, + "audio_speech": false, + "moderations": false, + "batches": false, + "rerank": false, + "a2a": false + } + }, "scx-ai": { "display_name": "SCX.ai (`scx-ai`)", "url": "https://docs.litellm.ai/docs/providers/scx_ai", diff --git a/tests/test_litellm/llms/openai_like/test_gitgot_provider.py b/tests/test_litellm/llms/openai_like/test_gitgot_provider.py new file mode 100644 index 00000000000..25aae9de538 --- /dev/null +++ b/tests/test_litellm/llms/openai_like/test_gitgot_provider.py @@ -0,0 +1,137 @@ +""" +Tests for GitGot provider configuration and integration. +""" + +import litellm + + +class TestGitGotProviderConfig: + def test_gitgot_in_provider_list(self): + from litellm import LlmProviders + + assert hasattr(LlmProviders, "GITGOT") + assert LlmProviders.GITGOT.value == "gitgot" + assert "gitgot" in litellm.provider_list + + def test_gitgot_json_config_exists(self): + from litellm.llms.openai_like.json_loader import JSONProviderRegistry + + assert JSONProviderRegistry.exists("gitgot") + + gitgot = JSONProviderRegistry.get("gitgot") + assert gitgot is not None + assert gitgot.base_url == "https://inference.gitgot.ai/v1" + assert gitgot.api_key_env == "GITGOT_API_KEY" + assert gitgot.api_base_env == "GITGOT_API_BASE" + + def test_gitgot_in_openai_compatible_providers(self): + from litellm.constants import openai_compatible_providers + + assert "gitgot" in openai_compatible_providers + + def test_gitgot_in_openai_compatible_endpoints(self): + from litellm.constants import openai_compatible_endpoints + + assert "https://inference.gitgot.ai/v1" in openai_compatible_endpoints + + def test_gitgot_provider_resolution(self): + from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider + + model, provider, api_key, api_base = get_llm_provider( + model="gitgot/openai/gpt-5-nano", + custom_llm_provider=None, + api_base=None, + api_key=None, + ) + + # GitGot model ids carry a vendor prefix, so only the leading "gitgot/" + # is stripped and the rest of the path is preserved. + assert model == "openai/gpt-5-nano" + assert provider == "gitgot" + assert api_base == "https://inference.gitgot.ai/v1" + + def test_gitgot_api_base_override(self): + from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider + + model, provider, api_key, api_base = get_llm_provider( + model="gitgot/openai/gpt-5-nano", + custom_llm_provider=None, + api_base="https://custom.gitgot.ai/v1", + api_key="gg-test", + ) + + assert provider == "gitgot" + assert api_base == "https://custom.gitgot.ai/v1" + assert api_key == "gg-test" + + def test_gitgot_model_prices_registered(self, local_model_cost_map): + from litellm import model_cost + + entry = model_cost["gitgot/openai/gpt-5-nano"] + assert entry["litellm_provider"] == "gitgot" + assert entry["mode"] == "chat" + # Costs in this file are per token, not per million. A per-million + # figure here would report the provider as a million times dearer than + # it is in every client that reads it. + assert 0 < entry["input_cost_per_token"] < 0.001 + assert 0 < entry["output_cost_per_token"] < 0.001 + assert entry["max_input_tokens"] > 0 + + def test_gitgot_cost_calculation(self, local_model_cost_map): + from litellm import completion_cost + from litellm.types.utils import Choices, Message, ModelResponse, Usage + + response = ModelResponse( + id="chatcmpl-test", + choices=[ + Choices( + finish_reason="stop", + index=0, + message=Message(content="hello", role="assistant"), + ) + ], + created=1234567890, + model="gitgot/openai/gpt-5-nano", + object="chat.completion", + usage=Usage( + prompt_tokens=1_000_000, + completion_tokens=1_000_000, + total_tokens=2_000_000, + ), + ) + + cost = completion_cost(completion_response=response) + # A million tokens each way should cost dollars, not thousands. + assert 0 < cost < 100 + + def test_gitgot_router_config(self): + from litellm import Router + + router = Router( + model_list=[ + { + "model_name": "gitgot-chat", + "litellm_params": { + "model": "gitgot/openai/gpt-5-nano", + "api_key": "test-key", + }, + } + ] + ) + + assert len(router.model_list) == 1 + assert router.model_list[0]["model_name"] == "gitgot-chat" + + def test_gitgot_endpoint_support_declared(self): + import json + from pathlib import Path + + support = json.loads( + ( + Path(litellm.__file__).parent.parent + / "provider_endpoints_support.json" + ).read_text() + )["providers"]["gitgot"] + + assert support["endpoints"]["chat_completions"] is True + assert support["endpoints"]["embeddings"] is True diff --git a/ui/litellm-dashboard/public/assets/logos/gitgot.svg b/ui/litellm-dashboard/public/assets/logos/gitgot.svg new file mode 100644 index 00000000000..c03cb6f12f9 --- /dev/null +++ b/ui/litellm-dashboard/public/assets/logos/gitgot.svg @@ -0,0 +1 @@ + diff --git a/ui/litellm-dashboard/src/components/provider_info_helpers.tsx b/ui/litellm-dashboard/src/components/provider_info_helpers.tsx index 72ec5990557..7eb5d886c7d 100644 --- a/ui/litellm-dashboard/src/components/provider_info_helpers.tsx +++ b/ui/litellm-dashboard/src/components/provider_info_helpers.tsx @@ -52,6 +52,7 @@ import runwayLogo from "../../public/assets/logos/runway.png"; import sambanovaLogo from "../../public/assets/logos/sambanova.svg"; import sapLogo from "../../public/assets/logos/sap.png"; import scxAiLogo from "../../public/assets/logos/scx_ai.svg"; +import gitgotLogo from "../../public/assets/logos/gitgot.svg"; import snowflakeLogo from "../../public/assets/logos/snowflake.svg"; import sonioxLogo from "../../public/assets/logos/soniox.svg"; import togetheraiLogo from "../../public/assets/logos/togetherai.svg"; @@ -160,6 +161,7 @@ export enum Providers { Sambanova = "Sambanova", SAP = "SAP Generative AI Hub", SCX_AI = "SCX.ai", + GitGot = "GitGot", Snowflake = "Snowflake", Soniox = "Soniox", TEXT_COMPLETION_CODESTRAL = "Text-Completion-Codestral", @@ -276,6 +278,7 @@ export const provider_map: Record = { Sambanova: "sambanova", SAP: "sap", SCX_AI: "scx-ai", + GitGot: "gitgot", Snowflake: "snowflake", Soniox: "soniox", TEXT_COMPLETION_CODESTRAL: "text-completion-codestral", @@ -373,6 +376,7 @@ export const providerLogoMap: Partial> = { [Providers.Sambanova]: sambanovaLogo.src, [Providers.SAP]: sapLogo.src, [Providers.SCX_AI]: scxAiLogo.src, + [Providers.GitGot]: gitgotLogo.src, [Providers.Snowflake]: snowflakeLogo.src, [Providers.Soniox]: sonioxLogo.src, [Providers.TEXT_COMPLETION_CODESTRAL]: mistralLogo.src, @@ -440,6 +444,7 @@ const providerPlaceholderMap: Partial> = { [Providers.RunwayML]: "runwayml/gen4_turbo", [Providers.SageMaker]: "sagemaker/jumpstart-dft-meta-textgeneration-llama-2-7b", [Providers.SCX_AI]: "scx-ai/GLM-5.2", + [Providers.GitGot]: "gitgot/openai/gpt-5-nano", [Providers.Snowflake]: "snowflake/mistral-7b", [Providers.Vertex_AI]: "gemini-pro", [Providers.VolcEngine]: "volcengine/",