Claude Fable 5.2 - Unifically

Claude Fable 5.2 is Anthropic’s top Claude model, released November 9, 2026, built for long-horizon agentic coding, multistep research, and document, spreadsheet, and slide work. It is up to 30% faster than Claude Fable 5.1. It takes text and image input, outputs text, and carries a 1M token context window with up to 128k output tokens. Adaptive thinking is always on. Try it in the browser: Claude Fable 5.2 API playground.

Model

anthropic/claude-fable-5-2


Provider	Anthropic
Name	Claude Fable 5.2
Context window	1M tokens
Max output	128k tokens

Supported Endpoints

All three API formats are supported:

Chat Completions — POST /v1/chat/completions
Responses — POST /v1/responses
Messages — POST /v1/messages

Send LLM requests to https://direct-api.unifically.com, not https://api.unifically.com. The main host sits behind Cloudflare, and Cloudflare’s proxy timeout cuts most LLM requests short before the model has finished writing. When that happens you receive a truncated reply and are still charged for every token generated up to the cut-off. direct-api.unifically.com reaches the same API without the Cloudflare proxy, so long responses complete in full.

Example

curl -X POST https://direct-api.unifically.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "anthropic/claude-fable-5-2",
    "max_tokens": 4096,
    "messages": [
      {"role": "user", "content": "Plan the migration of this service from Python to Rust, then list the first three changes to make."}
    ]
  }'

Thinking cannot be turned off on this model. Forced tool use (tool_choice set to any or a named tool) is not supported, so keep tool_choice on auto and name the tool in the prompt. Leave out temperature, top_p, and top_k. Thinking blocks are bound to the model that produced them, so keep conversation history append-only.

Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.

​Model

​Supported Endpoints

​Example

Model

Supported Endpoints

Example