Claude Fable 5.1 API

Zurelay charges $3.50 per 1M input tokens and $17.50 per 1M output tokens, with cached input at $0.0875. Anthropic's list price is $10.00 input and $50.00 output, so you save 65%. The rate is the same at every prompt length, up to the full 1M-token window.

Yes. Zurelay serves claude-fable-5-1 at 65% below Anthropic's list price, paid from prepaid credit with no subscription. It is the same model, not a smaller substitute. You keep your code and change the base URL and key.

Create a Zurelay API key, set the base URL to https://api.zurelay.com/v1 and set the model to claude-fable-5-1. Chat completions, streaming and tool calls use the request shapes you know from OpenAI. Temperature and top_p have no effect, so Zurelay leaves them out. Anthropic's API refuses a forced tool_choice on this model, so when you force one (required, or a named function), Zurelay sends it as auto and tells the model which tool to call.

Yes. Set the Anthropic SDK's base URL, or ANTHROPIC_BASE_URL for Claude Code, to https://api.zurelay.com with no /v1, because the client adds /v1/messages itself. Authenticate with your Zurelay key and choose claude-fable-5-1 as the model. Anthropic notes that Claude Code runs Fable 5.1 at high effort by default.

Claude Fable 5.1 has a 1M-token context window, roughly 555k English words on Anthropic's current tokenizer, and returns up to 128K output tokens per request. Thinking counts toward the output limit, so set a large max_tokens at high effort and stream long responses.

For new work, use Claude Fable 5.2: Anthropic reports gains in coding, reasoning and vision, with a list price 20% lower per token. Stay on Fable 5.1 if you need results that match evals you already ran on it, or until you've checked that your code keeps conversation history append-only, which Fable 5.2 requires on every account when thinking blocks are passed back.

Anthropic built it for demanding reasoning and long-horizon agentic work: coding sessions that run for hours, multistep research, document, spreadsheet and slide work, vision on dense charts, and computer use. For routine traffic, Claude Opus 5.5 or Claude Sonnet 5.5 usually costs less per task.

The context window, output limit and list price per token are the same, and cache reads list at a quarter of the old rate. Three API changes can break code: Anthropic refuses forced tool choice (Zurelay sends it as auto, with the tool named), earlier models can't read Fable 5.1 thinking blocks, and editing earlier turns invalidates thinking blocks. Anthropic also notes fewer parallel tool calls in some agent loops and less markdown formatting in chat.

Yes. Streaming works on chat completions and on the Messages API; on chat completions, set stream_options.include_usage to get token counts at the end of the stream. Hard tasks at high effort can run long, so stream those requests. Each key can have its own monthly budget and requests-per-minute cap, and failed requests are retried on another route and never billed.

Yes. Your requests run on Claude Fable 5.1 itself. Zurelay doesn't swap in a different or smaller model. Only smart routing, which you turn on yourself, can answer with a close alternative when the model is down, and the x-zurelay-model header names the model that answered. Output is sampled, so exact wording varies between calls on any API. Zurelay is an independent service and is not affiliated with or endorsed by Anthropic.