From e54f228ed87b78659bee066ccd2f4e36bfe97926 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 13:46:15 -0700 Subject: [PATCH] chore(prices): sync Baseten prices: 4 models, 4 new [enrichment failed: Baseten, 3 held] (#42578) baseten/deepseek-ai/DeepSeek-V4-Flash-0731: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost baseten/deepseek-ai/DeepSeek-V4-Pro: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost baseten/deepseek-ai/DeepSeek-V4-Pro-0813: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost baseten/zai-org/GLM-5.2-Fast: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 68 +++++++++++++++++++ model_prices_and_context_window.json | 68 +++++++++++++++++++ 2 files changed, 136 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a2863f6b0dc..b8ca5ff27c7 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -77665,5 +77665,73 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true + }, + "baseten/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.6e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.48e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.32e-07, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/zai-org/GLM-5.2-Fast": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a2863f6b0dc..b8ca5ff27c7 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -77665,5 +77665,73 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true + }, + "baseten/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.6e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.48e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.32e-07, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/zai-org/GLM-5.2-Fast": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true } }