{
  "$schema": "./_schema.json",
  "id": "cerebras",
  "label": "Cerebras",
  "docs": "https://inference-docs.cerebras.ai/",
  "console": "https://cloud.cerebras.ai/platform",
  "priority": 15,
  "baseUrl": "https://api.cerebras.ai/v1",
  "auth": { "type": "bearer", "envKeys": ["CEREBRAS_API_KEY"] },
  "limits": { "rpm": 30, "rpd": 14400, "tpm": 60000, "tpd": 1000000 },
  "limitsSource": "docs",
  "verifiedOn": "2026-08-16",
  "modelsEndpoint": "/models",
  "modelsPath": "data[].id",
  "notes": "Largest daily token budget of the free tiers (~1M tokens/day), no card required. Cerebras reports windowed rate-limit headers (x-ratelimit-limit-tokens-day and friends), so calibration gets exact per-key numbers after the first request.",
  "models": [
    { "id": "llama-3.3-70b", "label": "Llama 3.3 70B", "alias": ["fast", "big"], "context": 65536, "caps": ["chat", "tools", "json"], "priority": 10 }
  ]
}