Skip to content
Docs menu

LLM models

Claude Fable 5

On this page

Claude Fable 5 — frontier reasoning and generation through one API.

modelIdclaude-fable-5
Modalitytext
PricingSee this model on the Pricing page for the current per-call price (with your markup).

Operations

OperationmodelIdEndpointRequired input
Defaultclaude-fable-5POST /api/v1/generateprompt
Poll taskGET /api/v1/task/{id}?model=claude-fable-5

Input parameters

FieldTypeRequiredValues / example
promptstringYesText 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)
memorybooleanNoAutomatically append previous messages to maintain multi-turn context. May increase token usage. (true/false) (default: false)
thinkingbooleanNoInclude the model's thinking process in the response (true/false) (default: true)
max_tokensnumberNoOptional Claude output token limit. Leave empty to use the default of 4096. (range 1-128000)
streambooleanNoSend 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)
imagesstring[]NoUp 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_searchbooleanNoWeb 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)
systemstringNoSystem instruction for the model. Defaults to "You are Claude Fable 5, developed by Anthropic." when omitted.
messagesarrayNoA 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}}'