📡 AI API Radar

Live AI API prices, status & the only public price history

Per-model $/M-token pricing, context windows and real-time operational status across 11 LLM providers — plus the time-series nobody else keeps, so you can see who's cutting prices in the model price war.

Find the cheapest model →Agent-callable API & MCP

Tracking 44 models across 11 providers · 2 snapshots accrued · prices verified per-provider on the dates shown below.

Cheapest models right now (blended, output-weighted 3:1)

ModelProviderInput /1MOutput /1MContextBlended
Command R7B (12-2024) Cohere $0.04$0.15128K $0.12
GPT-OSS 20B Groq $0.08$0.3131K $0.24
DeepSeek V4 Flash DeepSeek $0.14$0.281M $0.25
Llama 3.3 70B (via OpenRouter) OpenRouter $0.1$0.32131K $0.27
Llama 4 Scout (17Bx16E) Groq $0.11$0.34131K $0.28
GPT-4.1 nano OpenAI $0.1$0.41M $0.33
Gemini 2.5 Flash-Lite Google Gemini $0.1$0.41.048576M $0.33
GPT-4o mini (legacy) OpenAI $0.15$0.6128K $0.49

→ Full cheapest-model comparison & task-tier picks

11
providers tracked
44
models priced
6h
refresh cadence
x402
agent-payable API

For AI agents: route to the cheapest model programmatically

An agent can call cheapest_model(task, min_context) over MCP (or HTTP) and route to the lowest-cost operational model automatically — pay-per-call via x402 (USDC on Base, no signup) or a self-serve key.

Developer API & MCP docs → · x402 agent catalog →