Claude Fable 5 access restored on AI Gateway
Quick Answer
Access to Claude Fable 5, the Mythos-class model by Anthropic, has been restored on AI Gateway following updated safety classifiers.
Quick Take
Users should be aware that routine tasks like coding may trigger these classifiers, and fallback models are available if requests are denied.
Key Points
- Claude Fable 5 access restored after US export control lift.
- Updated safety classifiers may trigger on routine coding tasks.
- Fallback models will be used if Fable 5 requests are denied.
- Prompts and completions retained for 30 days, no Zero Data Retention.
- Model name to call Fable 5 is 'anthropic/claude-fable-5'.
📖 Reader Mode
~1 min readAccess to Claude Fable 5, the Mythos-class model, has now been restored on AI Gateway following the US Government's decision to lift the export controls.
Fable 5 is the same model that was available between June 9 and June 12. What has changed is the safety classifiers, which are now updated and more robust.
In the near term, some routine tasks such as coding and debugging may trigger safety classifiers. To ensure requests are still serviced when the safety classifiers are triggered, use model fallbacks. AI Gateway will try each model in models in the stated order if Anthropic refuses the request to Fable 5.
To call Fable 5, use model name anthropic/claude-fable-5:
import { streamText } from 'ai';
const result = streamText({
model: 'anthropic/claude-fable-5',
prompt: 'Summarize this quarterly report and list the key risks.',
providerOptions: {
gateway: {
models: ['anthropic/claude-opus-4.8', 'anthropic/claude-sonnet-5'],
},
},
});
Call Fable 5 with model fallbacks. This request will fall back to Opus 4.8, then Sonnet 5, if the safety classifier is triggered.
Model fallbacks work on every API format: for more information on how to configure these, see the docs.
Anthropic does not support Zero Data Retention for the model, because some misuse patterns are only visible across cumulative requests, which real-time filters cannot catch on their own. Prompts and completions are retained for 30 days and are not used to train Claude. Read more in the data retention whitepaper.
— Originally published at vercel.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Vercel AI
See more →
The Agent Stack
The Agent Stack by Vercel AI provides essential building blocks for creating production-grade agents, enabling seamless integration across multiple AI models and secure operations. It features components like AI Gateway for model routing, Workflow SDK for durable execution, and Vercel Connect for scoped access, streamlining agent development and deployment across various platforms.
