The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Python ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyrustrust-aivertex-ai
feat(cost-map): add fireworks deepseek v4.1 flash 1017 us at the us-only premium (#47667)
berriai-litellm-provider-info-sync[bot]5c836d6e13d7
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.jsonindex b6521557f83..c6aea8ec98a 100644--- a/litellm/model_prices_and_context_window_backup.json+++ b/litellm/model_prices_and_context_window_backup.json@@ -76923,5 +76923,25 @@"supported_output_modalities": ["text"]+ },+ "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us": {+ "cache_read_input_token_cost": 9e-09,+ "cache_read_input_token_cost_priority": 1.125e-08,+ "input_cost_per_token": 4.5e-07,+ "input_cost_per_token_priority": 5.625e-07,+ "litellm_provider": "fireworks_ai",+ "max_input_tokens": 1048576,+ "max_output_tokens": 393216,+ "max_tokens": 393216,+ "mode": "chat",+ "output_cost_per_token": 1.8e-06,+ "output_cost_per_token_priority": 2.25e-06,+ "source": "https://docs.fireworks.ai/serverless/us-only-serverless",+ "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.jsonindex b6521557f83..c6aea8ec98a 100644--- a/model_prices_and_context_window.json+++ b/model_prices_and_context_window.json@@ -76923,5 +76923,25 @@"supported_output_modalities": ["text"]+ },+ "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us": {+ "cache_read_input_token_cost": 9e-09,+ "cache_read_input_token_cost_priority": 1.125e-08,+ "input_cost_per_token": 4.5e-07,+ "input_cost_per_token_priority": 5.625e-07,+ "litellm_provider": "fireworks_ai",+ "max_input_tokens": 1048576,+ "max_output_tokens": 393216,+ "max_tokens": 393216,+ "mode": "chat",+ "output_cost_per_token": 1.8e-06,+ "output_cost_per_token_priority": 2.25e-06,+ "source": "https://docs.fireworks.ai/serverless/us-only-serverless",+ "supports_function_calling": true,+ "supports_prompt_caching": true,+ "supports_reasoning": true,+ "supports_response_schema": true,+ "supports_tool_choice": true,+ "supports_vision": true}}