From 541e81de2fefb3581f4f7eef61db5beb58264657 Mon Sep 17 00:00:00 2001 From: Austin Varga <64624232+avarga1@users.noreply.github.com> Date: Wed, 8 Apr 2026 22:34:03 -0600 Subject: [PATCH] fix: expose reasoning effort fields in get_model_info + add together_ai/gpt-oss-120b (#25263) * fix: expose reasoning effort fields in get_model_info and add together_ai/gpt-oss-120b - litellm/utils.py: pass supports_none_reasoning_effort and supports_xhigh_reasoning_effort through _get_model_info_helper so get_model_info() returns them (previously silently dropped). Fixes #25096. - model_prices_and_context_window.json: add together_ai/openai/gpt-oss-120b with supports_reasoning: true so reasoning_effort is accepted for this model without requiring drop_params. Fixes #25132. Co-Authored-By: Claude Sonnet 4.6 * fix: consolidate duplicate together_ai/openai/gpt-oss-120b entry and sync backup file * fix: link commit to GitHub account for CLA verification --------- Co-authored-by: Austin Varga Co-authored-by: Claude Sonnet 4.6 --- litellm/model_prices_and_context_window_backup.json | 5 ++++- litellm/utils.py | 2 ++ model_prices_and_context_window.json | 5 ++++- 3 files changed, 10 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d781c91992..22368f7a2f 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -28551,12 +28551,15 @@ "together_ai/openai/gpt-oss-120b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.together.ai/models/gpt-oss-120b", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, diff --git a/litellm/utils.py b/litellm/utils.py index f902644e76..3b5abbbdda 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -5872,6 +5872,8 @@ def _get_model_info_helper( # noqa: PLR0915 supports_web_search=_model_info.get("supports_web_search", None), supports_url_context=_model_info.get("supports_url_context", None), supports_reasoning=_model_info.get("supports_reasoning", None), + supports_none_reasoning_effort=_model_info.get("supports_none_reasoning_effort", None), + supports_xhigh_reasoning_effort=_model_info.get("supports_xhigh_reasoning_effort", None), supports_computer_use=_model_info.get("supports_computer_use", None), search_context_cost_per_query=_model_info.get( "search_context_cost_per_query", None diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index cfdb2911fd..334aa157fa 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -28536,12 +28536,15 @@ "together_ai/openai/gpt-oss-120b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.together.ai/models/gpt-oss-120b", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true },