# Fireworks AI — limits, quotas, pricing and capabilities

Canonical site: https://fireworks.ai
Facts: 6
Generated: 2026-10-07T03:18:11.461Z

| key | value | unit | plan | status | last_verified_at | source |
| --- | --- | --- | --- | --- | --- | --- |
| ai.model.context_window_tokens | 131072 | tokens | inference/serverless | verified | 2026-10-05T03:45:18.97+00:00 | https://fireworks.ai/pricing |
| ai.model.vision_input | true |  | inference/serverless | verified | 2026-10-05T03:45:18.97+00:00 | https://fireworks.ai/pricing |
| api.public_api.available | true |  | inference/serverless | verified | 2026-10-05T03:45:19.488+00:00 | https://docs.fireworks.ai/guides/quotas_usage/rate-limits |
| api.rate_limit.requests_per_minute | 600 | requests/minute | inference/serverless | verified | 2026-10-05T03:45:19.488+00:00 | https://docs.fireworks.ai/guides/quotas_usage/rate-limits |
| pricing.unit.input_tokens_per_million | 0.22 | USD | inference/serverless | verified | 2026-10-05T03:45:18.97+00:00 | https://fireworks.ai/pricing |
| pricing.unit.output_tokens_per_million | 0.22 | USD | inference/serverless | verified | 2026-10-05T03:45:18.97+00:00 | https://fireworks.ai/pricing |

Machine endpoints: /api/public/v1/providers/fireworks-ai, /api/public/v1/facts?provider=fireworks-ai