From 4b51e5787c781f43c221167126388593fd3580da Mon Sep 17 00:00:00 2001 From: Tasmay Pankaj Tibrewal <85983760+Tasmay-Tibrewal@users.noreply.github.com> Date: Fri, 15 Aug 2025 04:33:49 +0530 Subject: [PATCH 1/6] added qwen3, deepseek r1 0528 throughput, glm 4.5 and gpt oss models --- model_prices_and_context_window.json | 88 ++++++++++++++++++++++++++++ 1 file changed, 88 insertions(+) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 9668053888..5e43113113 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -14649,6 +14649,50 @@ "mode": "chat", "supports_tool_choice": true }, + "deepseek-ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-06, + "max_input_tokens": 262000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" + }, + "deepseek-ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 2e-06, + "max_input_tokens": 256000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" + }, + "deepseek-ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 3e-06, + "max_input_tokens": 256000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" + }, + "deepseek-ai/Qwen/Qwen3-235B-A22B-fp8-tput": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "max_input_tokens": 40000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput" + }, "together_ai/deepseek-ai/DeepSeek-V3": { "input_cost_per_token": 1.25e-06, "output_cost_per_token": 1.25e-06, @@ -14673,6 +14717,17 @@ "mode": "chat", "supports_tool_choice": true }, + "deepseek-ai/DeepSeek-R1-0528-tput": { + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 2.19e-06, + "max_input_tokens": 128000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/deepseek-r1-0528-throughput" + }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { "litellm_provider": "together_ai", "supports_function_calling": true, @@ -14690,6 +14745,39 @@ "mode": "chat", "source": "https://www.together.ai/models/kimi-k2-instruct" }, + "together_ai/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "max_input_tokens": 128000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "source": "https://www.together.ai/models/gpt-oss-120b" + }, + "together_ai/OpenAI/gpt-oss-20B": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2e-07, + "max_input_tokens": 128000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "source": "https://www.together.ai/models/gpt-oss-20b" + }, + "together_ai/zai-org/GLM-4.5-Air-FP8": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.1e-06, + "max_input_tokens": 128000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "source": "https://www.together.ai/models/glm-4-5-air" + }, "ollama/codegemma": { "max_tokens": 8192, "max_input_tokens": 8192, From a85ab9d2044e34514982396210ea95ad8a91e99a Mon Sep 17 00:00:00 2001 From: Tasmay Pankaj Tibrewal <85983760+Tasmay-Tibrewal@users.noreply.github.com> Date: Fri, 15 Aug 2025 04:34:55 +0530 Subject: [PATCH 2/6] added qwen3, deepseek r1 0528 throughput, glm 4.5 and gpt oss models --- ...odel_prices_and_context_window_backup.json | 88 +++++++++++++++++++ 1 file changed, 88 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 9668053888..5e43113113 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -14649,6 +14649,50 @@ "mode": "chat", "supports_tool_choice": true }, + "deepseek-ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-06, + "max_input_tokens": 262000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" + }, + "deepseek-ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 2e-06, + "max_input_tokens": 256000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" + }, + "deepseek-ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 3e-06, + "max_input_tokens": 256000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" + }, + "deepseek-ai/Qwen/Qwen3-235B-A22B-fp8-tput": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "max_input_tokens": 40000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput" + }, "together_ai/deepseek-ai/DeepSeek-V3": { "input_cost_per_token": 1.25e-06, "output_cost_per_token": 1.25e-06, @@ -14673,6 +14717,17 @@ "mode": "chat", "supports_tool_choice": true }, + "deepseek-ai/DeepSeek-R1-0528-tput": { + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 2.19e-06, + "max_input_tokens": 128000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "supports_tool_choice": false + "source": "https://www.together.ai/models/deepseek-r1-0528-throughput" + }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { "litellm_provider": "together_ai", "supports_function_calling": true, @@ -14690,6 +14745,39 @@ "mode": "chat", "source": "https://www.together.ai/models/kimi-k2-instruct" }, + "together_ai/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "max_input_tokens": 128000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "source": "https://www.together.ai/models/gpt-oss-120b" + }, + "together_ai/OpenAI/gpt-oss-20B": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2e-07, + "max_input_tokens": 128000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "source": "https://www.together.ai/models/gpt-oss-20b" + }, + "together_ai/zai-org/GLM-4.5-Air-FP8": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.1e-06, + "max_input_tokens": 128000, + "litellm_provider": "together_ai", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_parallel_function_calling": false, + "mode": "chat", + "source": "https://www.together.ai/models/glm-4-5-air" + }, "ollama/codegemma": { "max_tokens": 8192, "max_input_tokens": 8192, From d20391101b3a5024ee1aeb33d1218fce9f194830 Mon Sep 17 00:00:00 2001 From: Tasmay Pankaj Tibrewal <85983760+Tasmay-Tibrewal@users.noreply.github.com> Date: Fri, 15 Aug 2025 04:43:52 +0530 Subject: [PATCH 3/6] fixed together ai provider name mistake --- model_prices_and_context_window.json | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 5e43113113..071ade6e5a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -14649,7 +14649,7 @@ "mode": "chat", "supports_tool_choice": true }, - "deepseek-ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { + "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-06, "max_input_tokens": 262000, @@ -14660,7 +14660,7 @@ "supports_tool_choice": false "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" }, - "deepseek-ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "input_cost_per_token": 2e-06, "output_cost_per_token": 2e-06, "max_input_tokens": 256000, @@ -14671,7 +14671,7 @@ "supports_tool_choice": false "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" }, - "deepseek-ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { "input_cost_per_token": 6.5e-07, "output_cost_per_token": 3e-06, "max_input_tokens": 256000, @@ -14682,7 +14682,7 @@ "supports_tool_choice": false "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" }, - "deepseek-ai/Qwen/Qwen3-235B-A22B-fp8-tput": { + "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-07, "max_input_tokens": 40000, @@ -14717,7 +14717,7 @@ "mode": "chat", "supports_tool_choice": true }, - "deepseek-ai/DeepSeek-R1-0528-tput": { + "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { "input_cost_per_token": 5.5e-07, "output_cost_per_token": 2.19e-06, "max_input_tokens": 128000, From 0a83aecb5c334a514ca87181dcb7682cf16a8f00 Mon Sep 17 00:00:00 2001 From: Tasmay Pankaj Tibrewal <85983760+Tasmay-Tibrewal@users.noreply.github.com> Date: Fri, 15 Aug 2025 04:44:43 +0530 Subject: [PATCH 4/6] fixed together ai provider name mistake --- litellm/model_prices_and_context_window_backup.json | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 5e43113113..071ade6e5a 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -14649,7 +14649,7 @@ "mode": "chat", "supports_tool_choice": true }, - "deepseek-ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { + "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-06, "max_input_tokens": 262000, @@ -14660,7 +14660,7 @@ "supports_tool_choice": false "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" }, - "deepseek-ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "input_cost_per_token": 2e-06, "output_cost_per_token": 2e-06, "max_input_tokens": 256000, @@ -14671,7 +14671,7 @@ "supports_tool_choice": false "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" }, - "deepseek-ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { "input_cost_per_token": 6.5e-07, "output_cost_per_token": 3e-06, "max_input_tokens": 256000, @@ -14682,7 +14682,7 @@ "supports_tool_choice": false "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" }, - "deepseek-ai/Qwen/Qwen3-235B-A22B-fp8-tput": { + "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-07, "max_input_tokens": 40000, @@ -14717,7 +14717,7 @@ "mode": "chat", "supports_tool_choice": true }, - "deepseek-ai/DeepSeek-R1-0528-tput": { + "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { "input_cost_per_token": 5.5e-07, "output_cost_per_token": 2.19e-06, "max_input_tokens": 128000, From d9105a99abb7dab774b5c3858aebf0407cab83cb Mon Sep 17 00:00:00 2001 From: Tasmay Pankaj Tibrewal <85983760+Tasmay-Tibrewal@users.noreply.github.com> Date: Fri, 15 Aug 2025 05:07:46 +0530 Subject: [PATCH 5/6] fixed comma delimeter issue --- model_prices_and_context_window.json | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 071ade6e5a..a39f81897b 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -14657,7 +14657,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" }, "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { @@ -14668,7 +14668,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" }, "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { @@ -14679,7 +14679,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" }, "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { @@ -14690,7 +14690,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput" }, "together_ai/deepseek-ai/DeepSeek-V3": { @@ -14725,7 +14725,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/deepseek-r1-0528-throughput" }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { From d8a9509890e5ed6c7d2e095946e14f939d90a1b5 Mon Sep 17 00:00:00 2001 From: Tasmay Pankaj Tibrewal <85983760+Tasmay-Tibrewal@users.noreply.github.com> Date: Fri, 15 Aug 2025 05:08:20 +0530 Subject: [PATCH 6/6] fixed comma delimeter issue --- litellm/model_prices_and_context_window_backup.json | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 071ade6e5a..a39f81897b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -14657,7 +14657,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" }, "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { @@ -14668,7 +14668,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" }, "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { @@ -14679,7 +14679,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" }, "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { @@ -14690,7 +14690,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput" }, "together_ai/deepseek-ai/DeepSeek-V3": { @@ -14725,7 +14725,7 @@ "supports_function_calling": false, "supports_parallel_function_calling": false, "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, "source": "https://www.together.ai/models/deepseek-r1-0528-throughput" }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": {