Claude Fable 5.1

Claude Fable 5.1 is Anthropic’s latest Fable model for demanding reasoning and long-horizon agentic work. Use the AnyFast model ID claude-fable-5-1 with the native Anthropic Messages API at POST /v1/messages.

Model specifications

Specification	Value
Model ID	`claude-fable-5-1`
Context window	1M tokens
Maximum output	128K tokens
Input → output	Text and images → text
Thinking	Adaptive, always on
Default effort	`high`
Effort levels	`low`, `medium`, `high`, `xhigh`, `max`
Reliable knowledge cutoff	June 2026

What changed from Fable 5

Stronger long-running work — Improved agentic coding, multistep research, document, spreadsheet, slide, vision, and computer-use tasks.
Lower cache-read cost upstream — Anthropic reduced cache-read pricing while keeping base input and output pricing unchanged.
Forced tool use is unavailable — tool_choice: {"type":"any"} and tool_choice: {"type":"tool"} return 400. Use auto or none.
Thinking blocks are conversation-bound — Keep prior turns append-only and pass thinking blocks back unchanged. Editing the system prompt, tools, or an earlier message can invalidate later thinking blocks.
One-way thinking compatibility — Fable 5.1 can read thinking blocks from earlier Claude models, but earlier models cannot read Fable 5.1 thinking blocks.

Quick example

curl https://www.anyfast.ai/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-fable-5-1",
    "max_tokens": 4096,
    "output_config": { "effort": "high" },
    "messages": [
      {
        "role": "user",
        "content": "Review this migration plan and identify the three highest-risk assumptions."
      }
    ]
  }'

import anthropic

client = anthropic.Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai"
)

message = client.messages.create(
    model="claude-fable-5-1",
    max_tokens=4096,
    output_config={"effort": "high"},
    messages=[
        {
            "role": "user",
            "content": "Review this migration plan and identify the three highest-risk assumptions."
        }
    ]
)

for block in message.content:
    if block.type == "text":
        print(block.text)

import anthropic

client = anthropic.Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai"
)

with client.messages.stream(
    model="claude-fable-5-1",
    max_tokens=4096,
    output_config={"effort": "high"},
    messages=[
        {"role": "user", "content": "Create a phased rollout plan for a database migration."}
    ],
) as stream:
    for text in stream.text_stream:
        print(text, end="")

Core parameters

Parameter	Type	Required	Description
`model`	string	Yes	Must be `claude-fable-5-1`.
`messages`	array	Yes	Conversation turns with `user` or `assistant` roles. Text, images, and tool results are supported.
`max_tokens`	integer	Yes	Maximum output tokens, including thinking and visible text. Range: 1–128000.
`output_config.effort`	string	No	Controls thinking depth. Supports `low`, `medium`, `high`, `xhigh`, and `max`; default is `high`.
`thinking.type`	string	No	Omit it or set it to `adaptive`. Thinking cannot be disabled.
`tools`	array	No	Tool definitions available to the model.
`tool_choice.type`	string	No	Supports `auto` and `none`. Forced `any` or a named `tool` is not supported.
`stream`	boolean	No	Enables SSE streaming. Default: `false`.
`stop_sequences`	array	No	Custom sequences that stop generation.

Adaptive thinking is always on. Omit thinking or send {"type":"adaptive"}. Both manual extended thinking with budget_tokens and {"type":"disabled"} return 400. Use output_config.effort to control reasoning depth.

Claude Fable 5.1 does not support non-default sampling values. Omit temperature, top_p, and top_k. Only temperature: 1 and top_p from 0.99 to 1 are accepted for backward compatibility; any top_k value returns 400. Assistant-response prefilling is also unsupported.

Tool use

Keep tool_choice at auto (the default) or use none. Tell the model in the prompt when a tool applies and describe its input schema precisely. Do not use any or a named forced tool choice.

Multi-turn conversations

When you return an assistant turn containing thinking blocks, send the entire turn back exactly as received. Treat the system prompt, tool definitions, and earlier messages as append-only. Changing content before a Fable 5.1 thinking block can return 400 with a conversation-binding error.

Anthropic released Claude Fable 5.1 on September 1, 2026. See the official model overview, what’s new, and prompting guide.

API Reference

View request fields, response blocks, and the interactive API playground.

Getting started

Model Introduction

Resources

Claude Fable 5.1

Model specifications

What changed from Fable 5

Quick example

Core parameters

Tool use

Multi-turn conversations

API Reference

​Model specifications

​What changed from Fable 5

​Quick example

​Core parameters

​Tool use

​Multi-turn conversations

API Reference

Model specifications

What changed from Fable 5

Quick example

Core parameters

Tool use

Multi-turn conversations