From 2727359a9ef5b6e058c668ba1477fd13c49df136 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 13:24:49 -0700 Subject: [PATCH] chore(prices): sync Baseten prices: 12 models, 9 new [enrichment failed: Baseten, 15 held] (#42558) baseten/deepseek-ai/DeepSeek-V4.1-Flash: 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/moonshotai/Kimi-K2.6: 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/moonshotai/Kimi-K2.7-Code: 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/moonshotai/Kimi-K3: 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/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B: 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/openai/gpt-oss-120b: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, cache_read_input_token_cost baseten/thinkingmachines/inkling: 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/thinkingmachines/inkling-small: 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-4.7: max_tokens, supports_vision, max_input_tokens, max_output_tokens, supports_reasoning, supports_tool_choice, supports_prompt_caching, supports_response_schema, supports_function_calling, cache_read_input_token_cost baseten/zai-org/GLM-5.2: 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-5.3: supports_reasoning baseten/zai-org/GLM-5.3-Flash: 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 | 182 +++++++++++++++++- model_prices_and_context_window.json | 182 +++++++++++++++++- 2 files changed, 358 insertions(+), 6 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 0e80d4732c8..a2863f6b0dc 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -31722,10 +31722,21 @@ "output_cost_per_token": 3.15e-06 }, "baseten/zai-org/GLM-4.7": { + "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 2.2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, "baseten/zai-org/GLM-4.6": { "input_cost_per_token": 6e-07, @@ -31752,10 +31763,21 @@ "output_cost_per_token": 2.5e-06 }, "baseten/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-07, "litellm_provider": "baseten", + "max_input_tokens": 128072, + "max_output_tokens": 128072, + "max_tokens": 128072, "mode": "chat", - "output_cost_per_token": 5e-07 + "output_cost_per_token": 5e-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-V3.1": { "input_cost_per_token": 5e-07, @@ -68322,7 +68344,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://www.baseten.co/pricing/", + "source": "https://inference.baseten.co/v1/models", "supported_modalities": [ "text", "image" @@ -68332,6 +68354,7 @@ ], "supports_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -77489,5 +77512,158 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.2e-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 + }, + "baseten/moonshotai/Kimi-K2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, + "max_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 4e-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 + }, + "baseten/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, + "max_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 4e-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 + }, + "baseten/moonshotai/Kimi-K3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 202800, + "max_output_tokens": 202800, + "max_tokens": 202800, + "mode": "chat", + "output_cost_per_token": 2.4e-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/thinkingmachines/inkling": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4.05e-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 + }, + "baseten/thinkingmachines/inkling-small": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.2e-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 + }, + "baseten/zai-org/GLM-5.2": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.4e-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 + }, + "baseten/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-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": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 0e80d4732c8..a2863f6b0dc 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -31722,10 +31722,21 @@ "output_cost_per_token": 3.15e-06 }, "baseten/zai-org/GLM-4.7": { + "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 2.2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, "baseten/zai-org/GLM-4.6": { "input_cost_per_token": 6e-07, @@ -31752,10 +31763,21 @@ "output_cost_per_token": 2.5e-06 }, "baseten/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-07, "litellm_provider": "baseten", + "max_input_tokens": 128072, + "max_output_tokens": 128072, + "max_tokens": 128072, "mode": "chat", - "output_cost_per_token": 5e-07 + "output_cost_per_token": 5e-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-V3.1": { "input_cost_per_token": 5e-07, @@ -68322,7 +68344,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://www.baseten.co/pricing/", + "source": "https://inference.baseten.co/v1/models", "supported_modalities": [ "text", "image" @@ -68332,6 +68354,7 @@ ], "supports_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -77489,5 +77512,158 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.2e-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 + }, + "baseten/moonshotai/Kimi-K2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, + "max_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 4e-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 + }, + "baseten/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, + "max_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 4e-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 + }, + "baseten/moonshotai/Kimi-K3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 202800, + "max_output_tokens": 202800, + "max_tokens": 202800, + "mode": "chat", + "output_cost_per_token": 2.4e-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/thinkingmachines/inkling": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4.05e-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 + }, + "baseten/thinkingmachines/inkling-small": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.2e-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 + }, + "baseten/zai-org/GLM-5.2": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.4e-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 + }, + "baseten/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-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": true } }