Anthropic: Claude Fable 5.2 · fastrouter

Claude Fable 5.2 is Anthropic's generally available, production-safeguarded model for demanding reasoning and long-horizon agentic work, sharing underlying weights with Claude Mythos 5.2. Typical uses include agent sessions that run for hours, multistep deep research, and analysis carried through to a finished document, spreadsheet, or deck. It accepts text, images, and files and returns text, with a 1M-token context window and up to 128K output tokens. Adaptive thinking is always on, with the effort parameter controlling reasoning depth (low, medium, high, xhigh, max; default: high). Forced tool use returns an error, and temperature, top_p, and top_k should be omitted. It is priced 20% below Claude Fable 5.1 and offers an optional fast mode with up to 2.5x faster output at 2x the standard price.

Base model All models on this base All models of the provider to the provider

Input, $/1M $8.00

Output, $/1M $40.00

Cache read $0.20

Cache write —

Context 1 000 000

Max output 128 000

Accepts files, images, text

Last checked 14.11.2026 12:00:15 UTC

Source provider's page

Price alerts

API

OpenAI-compatible API: the official OpenAI SDKs work with this base URL. Replace YOUR_API_KEY with your key from the provider.

API base URL	`https://go.fastrouter.ai/api/v1`
Endpoint	`https://go.fastrouter.ai/api/v1/chat/completions`
Model id	`anthropic/claude-fable-5.2`

curl

curl https://go.fastrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "anthropic/claude-fable-5.2", "messages": [{"role": "user", "content": "Hello!"}], "max_tokens": 256}'

Python

import requests

r = requests.post(
    "https://go.fastrouter.ai/api/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
      "model": "anthropic/claude-fable-5.2",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ],
      "max_tokens": 256
    },
)
print(r.json())

JavaScript

const r = await fetch("https://go.fastrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
  body: JSON.stringify({
    "model": "anthropic/claude-fable-5.2",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "max_tokens": 256
  }),
});
console.log(await r.json());

Request (JSON)

{
  "model": "anthropic/claude-fable-5.2",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 256
}

Response (JSON)

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "anthropic/claude-fable-5.2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hi! How can I help?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

The address is taken from the provider's model list; check it against the provider's documentation.

Provider's API documentation

Source: AI Rate Card, https://airatecard.com/en/c/offer%3Afastrouter%7Canthropic/claude-fable-5.2, prices checked 2026-11-14; seller's page: https://fastrouter.ai

Technical details

ID: offer:fastrouter|anthropic/claude-fable-5.2