Anthropicmessages

Claude Fable 5.2 (batch) API

Anthropic's most capable generally available model, built for long-horizon agentic engineering, scientific research and large-scale batch processing with a 1 million token context.

The model is aimed at ambitious, open-ended technical work. It takes on large, ambiguous problems across multiple repositories and large monorepos, shows strong architectural judgment, tests its own work while in progress, and questions inherited conclusions to find root causes that other models miss. It can act as a lead agent over multi-day ambiguous engineering work and coordinate hundreds to over a thousand subagents, using tools efficiently and maintaining its own integrity during long runs by building controls and flagging non-reproducible results.

Beyond software, Claude Fable 5.2 devises new analysis methods for difficult physics calculations, designs fully functional electronic devices, formalizes mathematical proofs, and runs autonomous research loops of measuring, trying and improving, including ablations, machine-learning metric hill climbing and verification of each change. It brings deep reasoning to quantitative finance, from multi-agent research to forecasting and analysis, and handles 3D worlds, hardware components, simulations, animations, narrated educational videos and robotics environments. It is best suited where judgment and accuracy matter most; Claude Opus 5.5 is recommended for everyday coding and knowledge work, and queries flagged in cybersecurity and biology are automatically routed to less capable models.

Limited timeFree trial

Open Playground ↗Create API Key ↗Getting started →

Updated: Nov 10, 2026

MODEL ID

claude-fable-5.2:batch

Context: 1M
Max output: 128K
Recommended API: messages
Input: text / image / file
Output: text

Highlights

1 million token context window
Up to 30% faster output than Fable 5.1
Coordinates over a thousand subagents
Handles text, image and PDF input
Batch processing for large-scale runs
Top rank on Vals Index

Providers

1 providers

Compare API prices across providers. Select a provider to view all charges and conditions.

Provider · Pricing details
				Uptime
	$4	$20	$0.1

What $10 buys

Input: 2.5M tokens
Output: 500K tokens

Estimated from current input and output prices, before discounts.

Benchmarks

Vals Index
Ranked 1st among 36 models
71.31%

Scores as published by the model provider.

Reasoning

Default effort: high
Always enabled: Yes
Available effort levels: max / xhigh / high / medium / low

Quick Start

Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.

Open Playground Create API Key

Get your API key

Create a key from your Felo API Platform account and set it as an environment variable.

export FELO_API_KEY="YOUR_API_KEY"

Make your first request

Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.

claude-fable-5.2:batch

This model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.

const response = await fetch("https://openapi.felo.ai/api/v1/messages", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.FELO_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "claude-fable-5.2:batch",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Using third-party SDKs

Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.

Enable streaming

Add stream: true to receive responses as server-sent events.

curl -N https://openapi.felo.ai/api/v1/messages \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-fable-5.2:batch",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "stream": true
}'

Endpoint

Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.

SurfaceMethodURL

Messages

Anthropic-compatible messages for Claude-style clients.

POST

https://openapi.felo.ai/api/v1/messages

Parameters

NameTypeDefaultDescription

modelstringclaude-fable-5.2:batchPublic model ID to call.

max_tokensinteger—Maximum generated tokens.

messagesarray—Conversation messages for Chat Completions.

stop———

toolsarray—Tool calling definitions following compatible schema.

reasoning———

verbosity———

tool_choicestring or object—Controls whether a tool should be called.

response_formatobject—Request structured output when supported.

reasoning_effort———

include_reasoning———

structured_outputs———

Frequently asked questions

What is Claude Fable 5.2 (batch)?

Claude Fable 5.2 is Anthropic's flagship generally available model, released on November 9, 2026. It accepts text, image and PDF input and returns text, with a context window of 1 million tokens. Compared with Claude Fable 5.1, it improves in coding, reasoning and vision, and generates output up to 30% faster. Batch processing makes large-scale runs cost-efficient, which suits workloads that need many long, parallel jobs rather than quick interactive turns. The model is aimed at ambitious, open-ended technical work. It takes on large, ambiguous problems across multiple repositories and large monorepos, shows strong architectural judgment, tests its own work while in progress, and questions inherited conclusions to find root causes that other models miss. It can act as a lead agent over multi-day ambiguous engineering work and coordinate hundreds to over a thousand subagents, using tools efficiently and maintaining its own integrity during long runs by building controls and flagging non-reproducible results. Beyond software, Claude Fable 5.2 devises new analysis methods for difficult physics calculations, designs fully functional electronic devices, formalizes mathematical proofs, and runs autonomous research loops of measuring, trying and improving, including ablations, machine-learning metric hill climbing and verification of each change. It brings deep reasoning to quantitative finance, from multi-agent research to forecasting and analysis, and handles 3D worlds, hardware components, simulations, animations, narrated educational videos and robotics environments. It is best suited where judgment and accuracy matter most; Claude Opus 5.5 is recommended for everyday coding and knowledge work, and queries flagged in cybersecurity and biology are automatically routed to less capable models.

How is usage billed?

Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.

What input types does Claude Fable 5.2 accept?

It accepts text, image and PDF input, and produces text output.

How large is the context window?

Anthropicclaude-haiku-4-5

Claude Haiku 4.5 is Anthropic's fastest, most cost-efficient Claude model, released October 15, 2025, with extended thinking, computer use, and strong coding performance.

Fast iteration and focused codingMulti-step tool use across filesCoding and well-defined subagent tasksCustomer support and real-time chat

Context

200K

Max output

64K

Input tokens

$1 / 1M tokens

Output tokens

$5 / 1M tokens

Highlights

Performance history+

What $10 buys

Benchmarks

Reasoning

Quick Start

Get your API key

Make your first request

Using third-party SDKs

Enable streaming

Endpoint

Parameters

Frequently asked questions

Related models

Claude Fable 5.2

Claude Haiku 5.5

Claude Sonnet 5.5

Claude Opus 5.5

Claude Fable 5.1

Claude Haiku 4.5