diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 3864bd08964..095f49cb991 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -39069,6 +39069,24 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tts-1": { "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", diff --git a/litellm/proxy/_lazy_openapi_snapshot.json b/litellm/proxy/_lazy_openapi_snapshot.json index e30750ef565..1963c7799a2 100644 --- a/litellm/proxy/_lazy_openapi_snapshot.json +++ b/litellm/proxy/_lazy_openapi_snapshot.json @@ -15038,6 +15038,17 @@ } ], "title": "Upstream Resource" + }, + "upstream_token_header": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Upstream Token Header" } }, "title": "MCPCredentials", @@ -17518,6 +17529,17 @@ } ], "title": "Upstream Resource" + }, + "upstream_token_header": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Upstream Token Header" } }, "title": "MCPCredentials", @@ -20352,6 +20374,17 @@ } ], "title": "Upstream Resource" + }, + "upstream_token_header": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Upstream Token Header" } }, "title": "MCPCredentials", @@ -23699,6 +23732,17 @@ } ], "title": "Upstream Resource" + }, + "upstream_token_header": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "title": "Upstream Token Header" } }, "title": "MCPCredentials", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 3864bd08964..095f49cb991 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -39069,6 +39069,24 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048575, + "max_output_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "tts-1": { "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", diff --git a/tests/test_litellm/test_together_ai_model_metadata.py b/tests/test_litellm/test_together_ai_model_metadata.py index e0379aead84..45f0370386b 100644 --- a/tests/test_litellm/test_together_ai_model_metadata.py +++ b/tests/test_litellm/test_together_ai_model_metadata.py @@ -15,6 +15,7 @@ COST_MAP_ADAPTER: Final = TypeAdapter(CostMap) SERVERLESS_CHAT_MODELS: Final = ( "together_ai/moonshotai/Kimi-K3", "together_ai/zai-org/GLM-5.2", + "together_ai/zai-org/GLM-5.3-Flash", "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813", "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731", "together_ai/MiniMaxAI/MiniMax-M3", @@ -110,6 +111,22 @@ def test_together_glm_52_pricing(cost_map: CostMap): assert info["supports_reasoning"] is True +def test_together_glm_53_flash_pricing_and_capabilities(cost_map: CostMap): + info = cost_map["together_ai/zai-org/GLM-5.3-Flash"] + assert info["input_cost_per_token"] == 1.5e-07 + assert info["output_cost_per_token"] == 5e-07 + assert info["cache_read_input_token_cost"] == 3e-08 + assert info["max_input_tokens"] == 1048575 + assert info["max_output_tokens"] == 1048575 + assert info["supports_function_calling"] is True + assert info["supports_parallel_function_calling"] is True + assert info["supports_prompt_caching"] is True + assert info["supports_tool_choice"] is True + assert info["supports_response_schema"] is True + assert info["supports_vision"] is True + assert info["supports_reasoning"] is True + + def test_together_multilingual_e5_embedding_entry(cost_map: CostMap): info = cost_map["together_ai/intfloat/multilingual-e5-large-instruct"] assert info["mode"] == "embedding" diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts index 670e4bfa942..25fbd53018a 100644 --- a/ui/litellm-dashboard/src/lib/http/schema.d.ts +++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts @@ -30221,6 +30221,8 @@ export interface components { token_exchange_profile?: string | null; /** Upstream Resource */ upstream_resource?: string | null; + /** Upstream Token Header */ + upstream_token_header?: string | null; }; /** * MCPEnvVar