About Claude Fable 5.2
Claude Fable 5.2 is the successor to Claude Fable 5.1 in Anthropic's Mythos-class tier, built for demanding reasoning and long-horizon agentic work. Typical uses are agent sessions that run for hours, multistep deep research, and analysis carried through to a finished document, spreadsheet, or deck. It costs less than Claude Fable 5.1. Anthropic positions Claude Opus 5.5 as the starting point for most workloads and Claude Fable 5.2 for tasks where Opus 5.5 at higher effort still falls short.
Adaptive thinking is always on and steered by the effort parameter (low through max, default high); the raw chain of thought is never returned. Forced tool use and sampling parameters such as temperature are not supported. Safety classifiers may decline requests in sensitive domains such as cybersecurity and biology, returning a refusal stop reason. Editing earlier turns invalidates thinking blocks, so conversation histories should be append-only. It accepts text and images and has a reliable knowledge cutoff of June 2026.
| Metric | Value |
|---|---|
| Context Length | 1,000,000 tokens |
| Max Output | 128,000 tokens |
| Multilingual | Yes |
Ready to build with Claude Fable 5.2?
Try Claude Fable 5.2 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "claude-fable-5-2",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'API endpoint
See the API reference for request and response formats.
https://hub.oxen.ai/api/ai/chat/completions