LLM models
Claude Fable 5
On this page
Claude Fable 5 — frontier reasoning and generation through one API.
| modelId | claude-fable-5 |
| Modality | text |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Default | claude-fable-5 | POST /api/v1/generate | prompt |
| Poll task | — | GET /api/v1/task/{id}?model=claude-fable-5 | — |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | Text value (example: Write the opening 150 words of a short story set in a night market where every stall sells a different kind of silence. Third person, present tense, one… — full value in the request example) |
| memory | boolean | No | Automatically append previous messages to maintain multi-turn context. May increase token usage. (true/false) (default: false) |
| thinking | boolean | No | Include the model's thinking process in the response (true/false) (default: true) |
| max_tokens | number | No | Optional Claude output token limit. Leave empty to use the default of 4096. (range 1-128000) |
| stream | boolean | No | Send true to receive the reply as an event stream (Content-Type: text/event-stream). Omit it and you get a single JSON response — streaming is opt-in on this endpoint. (true/false) (example: true) |
| images | string[] | No | Up to 4 images per message — JPEG, PNG, GIF or WebP, 5 MB each. Send each one as a data: URL or an https URL. Images are billed as input tokens. (image URL) |
| web_search | boolean | No | Web search feeds the results back as input tokens, so a searched turn typically costs many times a normal turn (measured: 18–87×). Billed per token as usual — nothing extra per search. (true/false) (default: false) |
| system | string | No | System instruction for the model. Defaults to "You are Claude Fable 5, developed by Anthropic." when omitted. |
| messages | array | No | A conversation instead of a single `prompt`: up to 20 objects of { "role", "content" }, where role is user, assistant or system. Send `prompt` or `messages`, not both. Do not flatten a conversation into one prompt with "User:" / "Assistant:" labels — the model reads that as a single message, and a model using web search then searches for the whole block instead of your question. |
Example request
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"claude-fable-5","input":{"prompt":"Write the opening 150 words of a short story set in a night market where every stall sells a different kind of silence. Third person, present tense, one concrete sensory detail per sentence, no adverbs, and end on a line that makes the reader want the next paragraph. Do not explain the premise — let it arrive through what the narrator notices.","memory":false,"thinking":true,"max_tokens":1,"stream":true,"images":["data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAIAAAACCAIAAAD91JpzAAAAFklEQVR4nGP8z4AATAxIHFQeMg8OAgB1yQIDpk8YwwAAAABJRU5ErkJggg=="],"web_search":false}}'