Claude Fable 5.2

Anthropic's Claude for demanding reasoning and long-horizon agentic work: text and image input, 1M-token context, thinking always on.

Claude Fable 5.2 is Anthropic's model for demanding reasoning and long-horizon agentic work, above Claude Opus in its current line. Send a prompt, or a chat history in messages, and get a text answer. It reads images in the chat (image_url parts); PDF documents go through the Messages API. It takes up to 1M tokens of context and writes up to 128K tokens per answer.

Set reasoning_effort to low, medium, high, xhigh or max (high when you send none). system_prompt sets instructions for the whole chat and max_tokens caps the answer. Set private_mode to true to keep the prompt and the answer out of FlyMyAI storage and logs (synchronous calls only).

Call it with a FlyMyAI key in three ways: the FlyMyAI API, the OpenAI-compatible Chat Completions endpoint, or Anthropic's own API under the model's address with the official Anthropic SDK (the Messages API). On the last two your request reaches Anthropic as you send it, so function tools, structured output, prompt caching and streaming work as Anthropic documents them for that API, and FlyMyAI stores neither the prompt nor the answer. Its Chat Completions endpoint is Anthropic's compatibility layer: it ignores reasoning_effort and has no prompt caching, so use the Messages API for either.

Thinking is always on and its raw text is never returned. Anthropic keeps requests to this model for 30 days. Not offered through FlyMyAI: tools Anthropic runs itself (web search, web fetch, code execution, the advisor), the MCP connector, the Files API, fallback models, fast mode, message threads and pinned inference regions. Billing follows the tokens Anthropic reports for each call: $8.00 input, $0.20 cached input and $40.00 output per 1M tokens, cache writes $10.00 ($16.00 kept for an hour).

Price: $8.00 per 1M input tokens, $40.00 per 1M output tokens, cached input $0.20 per 1M, cache writes $10.00 per 1M ($16.00 kept longer).

Run Claude Fable 5.2 via API

curl -X POST https://api.flymy.ai/api/v1/flymyai/claude-fable-5-2/predict \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

OpenAI-compatible API

Claude Fable 5.2 also speaks the OpenAI Chat Completions protocol: use the official OpenAI SDK with base URL https://api.flymy.ai/api/v1/flymyai/claude-fable-5-2/openai/v1 and your FlyMy.AI API key.

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.flymy.ai/api/v1/flymyai/claude-fable-5-2/openai/v1", api_key=os.environ["FLYMYAI_API_KEY"])
response = client.chat.completions.create(
    model="flymyai/claude-fable-5-2",
    messages=[{"role": "user", "content": "What is a vector database?"}],
)
print(response.choices[0].message.content)

OpenAI-compatible API docs

API documentation · Create a free account · Pricing

Related models