Skip to content

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]

fix(pricing): update baseten reflection/Beam-1.0 prices from the models API (#47784)

berriai-litellm-provider-info-sync[bot]1fcbb0355e76
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index fd72d209ffb..764cf397158 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -76709,14 +76709,14 @@
"supports_response_schema": true
},
"baseten/reflection/Beam-1.0": {
- "cache_read_input_token_cost": 1.3e-07,
- "input_cost_per_token": 1.3e-06,
+ "cache_read_input_token_cost": 4e-08,
+ "input_cost_per_token": 4e-07,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
- "output_cost_per_token": 4.3e-06,
+ "output_cost_per_token": 1.2e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index fd72d209ffb..764cf397158 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -76709,14 +76709,14 @@
"supports_response_schema": true
},
"baseten/reflection/Beam-1.0": {
- "cache_read_input_token_cost": 1.3e-07,
- "input_cost_per_token": 1.3e-06,
+ "cache_read_input_token_cost": 4e-08,
+ "input_cost_per_token": 4e-07,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
- "output_cost_per_token": 4.3e-06,
+ "output_cost_per_token": 1.2e-06,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,