From 75808575011977b27c684e6dda9ccdfcc8a581cb Mon Sep 17 00:00:00 2001 From: aiapienthusiast <327629069+aiapienthusiast@users.noreply.github.com> Date: Thu, 17 Sep 2026 11:59:27 +0400 Subject: [PATCH] fix(cheaperinference): copy the corrected cost map over the backup Byte-identical to the root cost map, as cost-map-guard requires. --- ...odel_prices_and_context_window_backup.json | 66 +++++++++---------- 1 file changed, 33 insertions(+), 33 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2a7d32a20b0..958593ed66b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2784,7 +2784,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/claude-sonnet-5": { "cache_creation_input_token_cost": 1.7e-06, @@ -2808,15 +2808,15 @@ "supports_vision": false }, "cheaperinference/glm-5.3-flash": { - "cache_creation_input_token_cost": 8.0568e-08, + "cache_creation_input_token_cost": 7.2511e-08, "cache_read_input_token_cost": 1.275e-08, - "input_cost_per_token": 8.0568e-08, + "input_cost_per_token": 7.2511e-08, "litellm_provider": "cheaperinference", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.68535e-07, + "output_cost_per_token": 2.41706e-07, "source": "https://cheaperinference.com/docs", "supported_endpoints": [ "/v1/chat/completions", @@ -2827,7 +2827,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "cheaperinference/glm-5.3": { "cache_creation_input_token_cost": 7.7e-07, @@ -2871,18 +2871,18 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/deepseek-v4.1-flash": { - "cache_creation_input_token_cost": 1.05e-07, - "cache_read_input_token_cost": 2.1e-09, - "input_cost_per_token": 1.05e-07, + "cache_creation_input_token_cost": 2.1e-07, + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-07, "litellm_provider": "cheaperinference", "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 4.2e-07, + "output_cost_per_token": 8.4e-07, "source": "https://cheaperinference.com/docs", "supported_endpoints": [ "/v1/chat/completions", @@ -2958,7 +2958,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/gpt-oss-120b": { "cache_creation_input_token_cost": 4e-08, @@ -3251,7 +3251,7 @@ "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/claude-opus-4.6": { "cache_creation_input_token_cost": 4.25e-06, @@ -3272,7 +3272,7 @@ "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/claude-opus-4.7": { "cache_creation_input_token_cost": 4.25e-06, @@ -3293,7 +3293,7 @@ "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/claude-opus-4.8": { "cache_creation_input_token_cost": 4.25e-06, @@ -3314,7 +3314,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/claude-opus-5-fast": { "cache_creation_input_token_cost": 8.5e-06, @@ -3356,7 +3356,7 @@ "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/claude-sonnet-4.6": { "cache_creation_input_token_cost": 2.55e-06, @@ -3377,7 +3377,7 @@ "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/deepseek-v4-flash": { "cache_creation_input_token_cost": 7.1388e-08, @@ -3767,7 +3767,7 @@ "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "cheaperinference/gpt-5-nano": { "cache_creation_input_token_cost": 4.0284e-08, @@ -3809,7 +3809,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/gpt-5.4-mini": { "cache_creation_input_token_cost": 5.25e-07, @@ -3830,18 +3830,18 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/gpt-5.4-nano": { - "cache_creation_input_token_cost": 1.4e-07, - "cache_read_input_token_cost": 1.4e-08, - "input_cost_per_token": 1.4e-07, + "cache_creation_input_token_cost": 1.61137e-07, + "cache_read_input_token_cost": 1.6114e-08, + "input_cost_per_token": 1.61137e-07, "litellm_provider": "cheaperinference", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 8.75e-07, + "output_cost_per_token": 1.007109e-06, "source": "https://cheaperinference.com/docs", "supported_endpoints": [ "/v1/chat/completions", @@ -3851,7 +3851,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "cheaperinference/gpt-5.4": { "cache_creation_input_token_cost": 1.75e-06, @@ -3872,7 +3872,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/gpt-5.5-pro": { "cache_creation_input_token_cost": 2.1e-05, @@ -3937,15 +3937,15 @@ "supports_vision": false }, "cheaperinference/muse-spark-1.2": { - "cache_creation_input_token_cost": 1.0625e-06, - "cache_read_input_token_cost": 1.0625e-07, - "input_cost_per_token": 1.0625e-06, + "cache_creation_input_token_cost": 8.75e-07, + "cache_read_input_token_cost": 1.05e-07, + "input_cost_per_token": 8.75e-07, "litellm_provider": "cheaperinference", "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 3.6125e-06, + "output_cost_per_token": 2.975e-06, "source": "https://cheaperinference.com/docs", "supported_endpoints": [ "/v1/chat/completions", @@ -3955,7 +3955,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "cheaperinference/qwen-3-8-27b": { "cache_creation_input_token_cost": 1.498e-07, @@ -3997,7 +3997,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "cheaperinference/qwen3-6-35b-a3b": { "cache_creation_input_token_cost": 7e-08, @@ -4018,7 +4018,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "cheaperinference/qwen3.6-27b": { "cache_creation_input_token_cost": 2.41706e-07,