Claude Fable 5.1 API

zurelay charges $3.50 per 1M input tokens and $17.50 per 1M output tokens, with cached input at $0.35. 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. Keep tool_choice on auto, since forcing a tool (required, or a named function) returns an error on this model, and leave temperature and top_p unset.

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.

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: forced tool choice returns an error, 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, and zurelay never swaps in a different or smaller model. 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.