From c39b95458eb7857e7bdabc8a74530e462230e4b4 Mon Sep 17 00:00:00 2001 From: Amaan Date: Wed, 28 Oct 2026 23:45:46 +0530 Subject: [PATCH] fix(zerogpu): flag vision on gpt-6-luna and qwen3.6-35b-a3b ZeroGPU reads image inputs on gpt-6-luna and qwen3.6-35b-a3b, so set supports_vision on both rows in both cost maps. Checked live on 2026-10-28, both models named the animal in an image_url photo, and the image showed up in their prompt token counts --- litellm/model_prices_and_context_window_backup.json | 6 ++++-- model_prices_and_context_window.json | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 34117f4670e..3ef33b2f564 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -65364,7 +65364,8 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "zerogpu/gpt-oss-120b": { "cache_read_input_token_cost": 3e-08, @@ -65447,7 +65448,8 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "together_ai/Qwen/Qwen3.8-Flash": { "input_cost_per_token": 1.5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 34117f4670e..3ef33b2f564 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -65364,7 +65364,8 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "zerogpu/gpt-oss-120b": { "cache_read_input_token_cost": 3e-08, @@ -65447,7 +65448,8 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "together_ai/Qwen/Qwen3.8-Flash": { "input_cost_per_token": 1.5e-07,