YepAPI
AI Models

Claude Fable 5.1

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows and knowledge work: long code refactors, front-end and visual tasks, and document-heavy analysis. Anthropic Frontier Agentic Coding & Knowledge Work, with a 1M token context window.

POST/v1/ai/chat
$0.01/call

Overview

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows and knowledge work: long code refactors, front-end and visual tasks, and document-heavy analysis. Anthropic Frontier Agentic Coding & Knowledge Work, with a 1M token context window.

PropertyValue
Model IDanthropic/claude-fable-5.1
Context Window1,000,000 tokens
Max Output128,000 tokens
Input Price$14.77 / 1M tokens
Output Price$73.85 / 1M tokens

Usage

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'anthropic/claude-fable-5.1',
    messages: [{ role: 'user', content: 'Refactor this React component tree to lift shared state into a context and remove prop drilling. Explain each step.' }],
  }),
});
const { data } = await res.json();
console.log(data.message.content);
curl -X POST https://api.yepapi.com/v1/ai/chat \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "anthropic/claude-fable-5.1", "messages": [{"role": "user", "content": "Refactor this React component tree to lift shared state into a context and remove prop drilling. Explain each step."}]}'

Request Body

ParameterTypeRequiredDescriptionDefault
modelstringYesModel ID (e.g. anthropic/claude-fable-5.1)—
messagesMessage[]YesArray of { role, content } objects—
maxTokensnumberNoMaximum tokens in the responseModel default
temperaturenumberNoSampling temperature (0.0–2.0)1.0
topPnumberNoNucleus sampling threshold1.0
frequencyPenaltynumberNoPenalize repeated tokens0
presencePenaltynumberNoPenalize tokens already present0
streambooleanNoEnable SSE streamingfalse
Info

All AI models use the /v1/ai/chat endpoint. Specify the model with the model field.

Response

{
  "ok": true,
  "data": {
    "model": "anthropic/claude-fable-5.1",
    "message": {
      "role": "assistant",
      "content": "Create a provider that owns the shared state and exposes it through a hook; wrap the subtree once; replace every prop chain that only forwards the value with the hook at the leaf that reads it. Keep props for values that genuinely differ per child, and add a test that renders a leaf without the provider to confirm the error message is clear."
    },
    "usage": {
      "promptTokens": 16,
      "completionTokens": 245,
      "totalTokens": 261
    }
  }
}

Streaming

Set "stream": true to receive Server-Sent Events. Each chunk contains a delta object:

data: {"delta":{"content":"Use"},"model":"anthropic/claude-fable-5.1","index":0}
data: [DONE]
Under the Hood

We handle auth, billing, and response normalization — you just send messages.

On this page