This server lets you query live LLM API pricing data across models and providers directly from your AI assistant:

• Search models — Find models by name, provider, ID, or category (flagship, reasoning, budget, coding, embedding, etc.), with optional open-source/proprietary filters.

• Get model pricing — Retrieve full pricing details for a specific model by ID, including input/output/cached price per 1M tokens, blended cost, context window, modality, release date, and a link to its pricing page.

• Compare models — Side-by-side comparison of 2–5 models on price, context window, and capabilities, with a verdict on which is cheapest for input, output, and blended workloads.

• Find cheapest models — Rank models by input, output, or blended cost, with optional filtering by category or open-source status.

• List providers — View all tracked AI providers (OpenAI, Anthropic, Google, Mistral, xAI, DeepSeek, etc.) along with descriptions and links to their official pricing pages.

Provides access to current and historical pricing data for Google's LLM models, including input/output/cached costs per million tokens, context windows, and model status.

Provides access to current and historical pricing data for Meta's LLM models, including input/output/cached costs per million tokens, context windows, and model status.

Provides access to current and historical pricing data for OpenAI's LLM models, including input/output/cached costs per million tokens, context windows, and model status.