Claude Fable 5 is Anthropic's most capable widely released model for the most demanding reasoning and long-horizon agentic coding — 1M context, 128K max output, always-on adaptive thinking, vision input, and standard /api/v1/chat/completions in one call. Pay-as-you-go from your reAPI balance.
Start with the prompt in the composer or choose an example.
Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.
One 1K-token prompt with a 1K-token answer at the cheapest tier.
Claude Fable 5 is Anthropic's most capable widely released model — a tier above Opus, built for the most demanding reasoning and long-horizon agentic work. It answers on an OpenAI-compatible /api/v1/chat/completions endpoint with a 1M-token context window, up to 128K output tokens per call, always-on adaptive thinking, vision input, and prompt caching. Usage is billed per million tokens, with input and output priced separately.
Real-world workflows and production use cases you can build and ship with this model.
Claude Fable 5 is built for the most demanding agentic work Anthropic's models can do — week-long refactors, codebase-scale migrations, and autonomous runs that must stay coherent across hundreds of steps. Where lighter models drift, Claude Fable 5 holds the plan, verifies its own output, and keeps going.
Read the API docs
When a problem sits past what Opus-tier models handle cleanly — deep multi-step reasoning, ambiguous specifications, high-stakes analysis — Claude Fable 5 is the model Anthropic positions above everything else it widely ships. Adaptive thinking is always on, and the effort parameter scales how much reasoning Claude Fable 5 invests in each call, up to max.
Feed entire codebases, long research packs, multi-file technical material, or full policy documents into a single Claude Fable 5 request. The 1M token context window is billed at standard per-token rates — no long-context premium — so analysis-heavy Claude Fable 5 workflows rarely need chunking.
Claude Fable 5 speaks OpenAI Chat Completions verbatim. Moving an existing OpenAI integration to Claude Fable 5 is a base URL, an API key, and a model-string change — not a platform rewrite. The same `messages` array, the same streaming format.
Claude Fable 5 sits a full tier above Claude Opus 4.8 — Anthropic's most capable widely released model, generally available since June 9, 2026. Route the hardest reasoning and the longest agentic runs to Claude Fable 5; send everyday premium coding to Opus-tier models on the same key.
A single reAPI key unlocks Claude Fable 5 alongside GPT-5.5, Claude Opus 4.8, Gemini 3.1 Pro, and every other frontier chat model on the platform. Compare vendors, add fallbacks, and route traffic per call with a configuration change instead of an integration project.
Claude Fable 5 is the tier above Opus — the most capable model Anthropic widely releases, launched June 9, 2026. Here is how it compares with Claude Opus 4.8, Anthropic's strongest Opus-tier model, based on Anthropic's own documentation.
Comparison reflects publicly documented behavior from Anthropic's Claude Fable 5 launch documentation and model overview at the time of writing. Model behavior and pricing can change; check the pricing card above and the API docs for current values.
Sign in to reAPI and create a key under API keys. That one key reaches Claude Fable 5 and every other model on the platform, billed from a single balance.
OpenPOST https://reapi.ai/api/v1/chat/completions with `model: "claude-fable-5"`, your `messages` array, and `max_tokens` set generously. The endpoint uses the standard chat-completions format, including streamed responses. Claude Fable 5 takes no sampling parameters — leave `temperature` and `top_p` out of the request.
OpenUse prompt caching for stable system prompts and recurring long inputs to bring repeated-context costs down. Reserve Claude Fable 5 for the highest-value calls and route everything else to a cheaper model on the same key.
Opencurl https://reapi.ai/api/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-fable-5",
"messages": [
{ "role": "user", "content": "Hello" }
],
"stream": true,
"max_tokens": 4096
}'Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.
401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.
Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.
A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.
Common questions about this model.
Explore more models in the same category.
Anthropic
From $8.00 per 1M tokens
Anthropic
From $2.40 per 1M tokens
Anthropic
From $4.00 per 1M tokens
Anthropic
From $2.00 per 1M tokens
Try it in the playground or grab an API key to integrate now.