diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c19ad6b4fdc..b046263bb1b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -63240,7 +63240,6 @@ "input_cost_per_token": 1e-08, "litellm_provider": "flexai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -63252,7 +63251,6 @@ "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.38e-07, "source": "https://platform.flex.ai/models", @@ -63260,28 +63258,12 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "flexai/DeepSeek-V4.1-Flash": { - "cache_read_input_token_cost": 1.54e-08, - "input_cost_per_token": 1.03e-07, - "litellm_provider": "flexai", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 7.15e-07, - "source": "https://platform.flex.ai/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true - }, "flexai/DeepSeek-V4.1-Flash-1017": { "cache_read_input_token_cost": 2.25e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://platform.flex.ai/models", @@ -63302,7 +63284,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.4e-07, "source": "https://platform.flex.ai/models", @@ -63317,7 +63298,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://platform.flex.ai/models", @@ -63332,7 +63312,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.6e-07, "source": "https://platform.flex.ai/models", @@ -63341,14 +63320,13 @@ "supports_tool_choice": true }, "flexai/GLM-5.2": { - "cache_read_input_token_cost": 1.449e-07, - "input_cost_per_token": 9.66e-07, + "cache_read_input_token_cost": 1.05e-07, + "input_cost_per_token": 7e-07, "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 3.036e-06, + "output_cost_per_token": 2.2e-06, "source": "https://platform.flex.ai/models", "supports_function_calling": true, "supports_reasoning": true, @@ -63360,7 +63338,6 @@ "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://platform.flex.ai/models", @@ -63375,7 +63352,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://platform.flex.ai/models", @@ -63389,7 +63365,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://platform.flex.ai/models", @@ -63412,7 +63387,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://platform.flex.ai/models", @@ -63425,7 +63399,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-08, "source": "https://platform.flex.ai/models", @@ -63438,7 +63411,6 @@ "litellm_provider": "flexai", "max_input_tokens": 204800, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://platform.flex.ai/models", @@ -63452,7 +63424,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://platform.flex.ai/models", @@ -63465,7 +63436,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://platform.flex.ai/models", @@ -63480,7 +63450,6 @@ "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://platform.flex.ai/models", @@ -63493,7 +63462,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://platform.flex.ai/models", @@ -63515,7 +63483,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://platform.flex.ai/models", @@ -63523,27 +63490,12 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "flexai/Qwen3-8B-FP8": { - "cache_read_input_token_cost": 1.75e-08, - "input_cost_per_token": 1.17e-07, - "litellm_provider": "flexai", - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "max_tokens": 40960, - "mode": "chat", - "output_cost_per_token": 4.55e-07, - "source": "https://platform.flex.ai/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "flexai/Qwen3-Coder-30B-A3B-Instruct-FP8": { "cache_read_input_token_cost": 1.05e-08, "input_cost_per_token": 7e-08, "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://platform.flex.ai/models", @@ -63556,7 +63508,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://platform.flex.ai/models", @@ -63571,7 +63522,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.flex.ai/models", @@ -63586,7 +63536,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 9.5e-07, "source": "https://platform.flex.ai/models", @@ -63601,7 +63550,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://platform.flex.ai/models", @@ -63616,7 +63564,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://platform.flex.ai/models", @@ -63631,7 +63578,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://platform.flex.ai/models", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index c19ad6b4fdc..b046263bb1b 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -63240,7 +63240,6 @@ "input_cost_per_token": 1e-08, "litellm_provider": "flexai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -63252,7 +63251,6 @@ "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.38e-07, "source": "https://platform.flex.ai/models", @@ -63260,28 +63258,12 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "flexai/DeepSeek-V4.1-Flash": { - "cache_read_input_token_cost": 1.54e-08, - "input_cost_per_token": 1.03e-07, - "litellm_provider": "flexai", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 7.15e-07, - "source": "https://platform.flex.ai/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true - }, "flexai/DeepSeek-V4.1-Flash-1017": { "cache_read_input_token_cost": 2.25e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://platform.flex.ai/models", @@ -63302,7 +63284,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.4e-07, "source": "https://platform.flex.ai/models", @@ -63317,7 +63298,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://platform.flex.ai/models", @@ -63332,7 +63312,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.6e-07, "source": "https://platform.flex.ai/models", @@ -63341,14 +63320,13 @@ "supports_tool_choice": true }, "flexai/GLM-5.2": { - "cache_read_input_token_cost": 1.449e-07, - "input_cost_per_token": 9.66e-07, + "cache_read_input_token_cost": 1.05e-07, + "input_cost_per_token": 7e-07, "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 3.036e-06, + "output_cost_per_token": 2.2e-06, "source": "https://platform.flex.ai/models", "supports_function_calling": true, "supports_reasoning": true, @@ -63360,7 +63338,6 @@ "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://platform.flex.ai/models", @@ -63375,7 +63352,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://platform.flex.ai/models", @@ -63389,7 +63365,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://platform.flex.ai/models", @@ -63412,7 +63387,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://platform.flex.ai/models", @@ -63425,7 +63399,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-08, "source": "https://platform.flex.ai/models", @@ -63438,7 +63411,6 @@ "litellm_provider": "flexai", "max_input_tokens": 204800, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://platform.flex.ai/models", @@ -63452,7 +63424,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://platform.flex.ai/models", @@ -63465,7 +63436,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://platform.flex.ai/models", @@ -63480,7 +63450,6 @@ "litellm_provider": "flexai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://platform.flex.ai/models", @@ -63493,7 +63462,6 @@ "litellm_provider": "flexai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://platform.flex.ai/models", @@ -63515,7 +63483,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://platform.flex.ai/models", @@ -63523,27 +63490,12 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "flexai/Qwen3-8B-FP8": { - "cache_read_input_token_cost": 1.75e-08, - "input_cost_per_token": 1.17e-07, - "litellm_provider": "flexai", - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "max_tokens": 40960, - "mode": "chat", - "output_cost_per_token": 4.55e-07, - "source": "https://platform.flex.ai/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "flexai/Qwen3-Coder-30B-A3B-Instruct-FP8": { "cache_read_input_token_cost": 1.05e-08, "input_cost_per_token": 7e-08, "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://platform.flex.ai/models", @@ -63556,7 +63508,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://platform.flex.ai/models", @@ -63571,7 +63522,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.flex.ai/models", @@ -63586,7 +63536,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 9.5e-07, "source": "https://platform.flex.ai/models", @@ -63601,7 +63550,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://platform.flex.ai/models", @@ -63616,7 +63564,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://platform.flex.ai/models", @@ -63631,7 +63578,6 @@ "litellm_provider": "flexai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://platform.flex.ai/models",