Name: Claude Fable 5.1 API
Brand: Anthropic

Overview

What Is Claude Fable 5.1 API?

Claude Fable 5.1 API is Anthropic's most capable model for demanding reasoning and long-horizon agentic work, available through AI/ML API on the standard chat completions endpoint. It carries a 1M token context window, always-on adaptive thinking, and stronger long-running agentic coding, multistep research and document work than Claude Fable 5. The model was released on September 1, 2026.

Core Features of Claude Fable 5.1 API

Always-On Adaptive Thinking

Adaptive thinking is always on rather than being a mode you opt into per request. The model allocates more internal deliberation to harder steps on its own, which suits work where the difficulty of each step is not known in advance.

Long-Horizon Agentic Work

Anthropic positions this release specifically around tasks that run for a long time without supervision: agentic coding sessions, multistep research, and document work that spans many turns. These are the areas where it is described as stronger than Claude Fable 5.

Large Context Window

The model accepts up to 1,000,000 tokens of input and returns up to 128,000 tokens of output. That input budget is large enough to hold entire repositories, long document sets or extended agent transcripts in a single request, without an external retrieval step.

API Pricing

Input: $13 / 1M tokens
Output: $65 / 1M tokens
Cached input: $0.325 / 1M tokens

Pricing is identical across the chat completions and messages endpoints, so the choice of endpoint does not change what a request costs.

Best Use Cases for Claude Fable 5.1 API

Agentic Coding

Long-running coding sessions where the model plans, edits and verifies across many steps rather than answering a single prompt.

Multistep Research

Research tasks that require gathering, comparing and reconciling information across many sources before producing a conclusion.

Document Work

Processing large document sets end to end, where the 1M token window removes the need to chunk material and stitch partial answers back together.

Claude Fable 5.1 vs Claude Fable 5

Both models share the same 1M token context window, the same 128,000 token output limit and the same input and output pricing of $13 and $65 per 1M tokens. The differences recorded in the API are the cached input rate, which drops from $1.3 to $0.325 per 1M tokens, and Anthropic's own claim of stronger long-running agentic coding, multistep research and document work.

Uptime and performance

Uptime (24h): 100%
Uptime (7d): 100%
Availability (24h): 99.0%
Error rate (24h): 1.0%
End-to-end latency (24h median): 32.2s
Time to first token (24h median): 1.2s
Throughput (24h median): 68.5 tok/s

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

Claude Fable 5.1 is documented as suited to long-running agentic coding, knowledge work, and research.

It is also described as a model for ambitious coding, long-horizon agents, and enterprise knowledge work, including software projects that span an entire codebase and multi-hour jobs across many tools.

The model is further documented for multistep research and document, spreadsheet, and slide work.

It is also listed as useful for scientific research, financial analysis, and vision tasks.

How to use Claude Fable 5.1 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to anthropic/claude-fable-5.1.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "anthropic/claude-fable-5.1",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())

const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "anthropic/claude-fable-5.1",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());

curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-fable-5.1","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.