# Keep an agent running through provider errors, rate limits and outages (slim)

> Keep an agent running through provider errors, rate limits and outages: 2 companies fully do it, 10 with a limit, 44 carry the tag. Every listing in Model APIs & inference with the reason and a source.

- Full: https://www.anchorterminal.com/niches/inference.failover-routing/index.md (~2,700 tokens) · this version ~380 tokens · JSON https://www.anchorterminal.com/niches/inference.failover-routing/index.json · canonical https://www.anchorterminal.com/niches/inference.failover-routing/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-15
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Two or three companies' docs show a full fit. Full fit: 2 companies, with a limit: 10, tagged: 44. Weight 16, 8 accounts.

Done when: A failed primary call falls through to the next model inside one request or one harness retry, the response says which provider served it, and the agent run finishes without the raw error reaching the user.
yes: eden-ai (Eden AI SAS)
yes: litellm (Berrie AI Incorporated)
caveat: antseed (Antseed Foundation)
caveat: blockrun-ai (BlockRun, Inc.)
caveat: cloudflare-ai-gateway (Cloudflare, Inc.)
caveat: deepinfra (Deep Infra Inc.)
caveat: elorian-glimpse (Elorian AI, Inc.)
caveat: hugging-face-inference-providers (Hugging Face, Inc.)
caveat: openrouter (OpenRouter, Inc.)
caveat: ramp-router (Ramp Business Corporation)
caveat: routerplus (EVO HQ Inc)
caveat: vercel-ai-gateway (Vercel Inc.)
unchecked: stepfun-api (STEPFUN TECHNOLOGY (HK) LIMITED)
unchecked: tencent-tokenhub (Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算（北京）有限责任公司))

Data: https://www.anchorterminal.com/api/v1/use-cases/inference.failover-routing.json
