Fallback model
A fallback model is a second id a client tries when the first call returns an error. LiteLLM and OpenRouter document that list, and provider deprecation pages do not switch your request to the replacement.
Last reviewed . Publisher: SunsetDiff. A source line names the day that page was read.
The rows below are copied from this site's model records. A shutdown cell is the date stored for that provider, not a date copied from another host.
Libraries that document a fallback list
LiteLLM tries the model argument first, then each entry in fallbacks, in order. The first success is returned. If every entry fails, completion raises.
OpenRouter's models array is tried in order when the first model returns an error. Errors that trigger a fallback include context length, moderation, rate limits, and downtime. The response model field is the id that actually ran.
The Vercel AI SDK OpenAI guide and LangChain's ChatOpenAI page document the model string. They do not document a fallback list. LangChain's chat integrations page says routers such as OpenRouter and LiteLLM offer automatic fallbacks.
Sources: LiteLLM reliable completions , OpenRouter model fallbacks , checked October 20, 2026.
What the providers do instead
Bedrock says migration will not happen automatically. You change the model id before the EOL date.
Azure can auto-upgrade a Standard deployment onto a newer model version. That is an upgrade of the deployment, not a client fallback list, and it does not apply to provisioned deployments.
OpenAI, Anthropic, and Gemini name a replacement on the deprecation page. Your request still sends one model id unless your own client tries a second id.
Sources: Bedrock model lifecycle , Foundry Models lifecycle , OpenAI deprecations , Anthropic model deprecations , checked October 22, 2026.
Rows from this dataset
Official replacements in the dataset. A fallback list is something you configure. These ids are the ones the provider named.
| Model | Provider | Stored status | Shutdown | Replacement |
|---|---|---|---|---|
| code-cushman-001 | OpenAI | retired | 2023-03-23 | gpt-4o · diff |
| claude-3-5-haiku-20241022 | Anthropic | retired | 2026-02-19 | claude-haiku-4-5-20251001 · diff |
| embedding-001 | Google Gemini API | retired | 2025-10-30 | gemini-embedding-2 · diff |
| chat-bison | Google Vertex AI | retired | 2025-04-21 | gemini-2.5-flash-lite · diff |
gpt-5-chat (2025-10-03) gpt-5-chat-2025-10-03 | Azure OpenAI | retired | 2026-05-13 | gpt-chat-latest · diff |
Codestral Mamba 7B (0.1) open-codestral-mamba | Mistral | retired | 2025-06-06 | codestral-2405 · diff |