Claude Fable 5.2

Claude Fable 5.2 is Anthropic's latest Fable model, with a 1M-token context window, 128K max output and always-on adaptive thinking. It accepts text and images and returns text.

Input / output priceUp to 15% off: ~~$8.00 / $40.00~~$6.80 / $34.00 per 1M
Context: 1M tokens
Released: Nov 9, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "anthropic/claude-fable-5.2".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="anthropic/claude-fable-5.2",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "anthropic/claude-fable-5.2",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "anthropic/claude-fable-5.2",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

2 providers, cheapest first, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
Anthropic15% off`anthropic/claude-fable-5.2`	1M	~~$8.00/M~~$6.80/M	~~$40.00/M~~$34.00/M	~~$0.20/M~~$0.17/M
Perplexity`perplexity/anthropic/claude-fable-5-2`	—	$8.00/M	$40.00/M	$0.20/M	—

Is a provider down? Anthropic status, Perplexity status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input: $7.40 per 1M
Average output: $37.00 per 1M
Average cache read: $0.18 per 1M
Average cache write: $8.50 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$8.00/MPerplexityLowest$6.80/MAnthropic

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

572tokens/sacross providers

Faster than 92% of the other 430 models on the gateway

Time to first token

Lower is better

2.8sacross providers

Faster than 30% of the other 119 models on the gateway

Response latency

Lower is better

13sacross providers

Faster than 19% of the other 492 models on the gateway

Benchmarks

The Respan Index plus 17 published scores from 7 sources, each linked to where it was published.

81.0/ 100

Respan Index#1 of 169

169 ranked models. The shaded band is this model's 95% interval, 77.2 to 84.2.

Published scores

Benchmark	Score	Source	Published
Terminal-Bench Science 0.1Anthropic	74.6%	Anthropic	Nov 9, 2026
FrontierSWE v2Anthropic	69.9%	Anthropic	Nov 9, 2026
FrontierSWE V2Proximal Labs	69.9%	Proximal Labs	Nov 10, 2026
Terminal-Bench 4.0Vals AI	65.2%	Vals AI	Nov 10, 2026

Benchmark	Score	Source	Published
APEX-AgentsMercor	80.1%	Mercor	Nov 11, 2026

Benchmark	Score	Source	Published
SimpleBenchSimpleBench	94.9%	SimpleBench	Nov 10, 2026
GPQA DiamondEpoch AI	93.9%	Epoch AI	Nov 10, 2026
EBR-benchEpoch AI	90.5%	Epoch AI	Nov 10, 2026
Mystery Game PuzzlesEpoch AI	90%	Epoch AI	Nov 10, 2026
Chess PuzzlesEpoch AI	79%	Epoch AI	Nov 10, 2026
Humanity's Last Exam (with tools)Anthropic	74.2%	Anthropic	Nov 9, 2026

Benchmark	Score	Source	Published
FrontierMath Tier 4 v2Epoch AI	100%	Epoch AI	Nov 10, 2026
OTIS Mock AIME 2024-2025Epoch AI	99.7%	Epoch AI	Nov 10, 2026
FrontierMath Tiers 1-3 v2Epoch AI	95.1%	Epoch AI	Nov 10, 2026

Benchmark	Score	Source	Published
SimpleQA VerifiedEpoch AI	94%	Epoch AI	Nov 10, 2026

Benchmark	Score	Source	Published
Furniture AssemblyEpoch AI	90%	Epoch AI	Nov 10, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1836 Elo · #1 of 118	LMArena	Nov 10, 2026

How the Respan Index works

How Claude compares: Claude vs Gemini, Claude vs Grok, Claude vs GPT

Apps

Use Claude Fable 5.2 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Claude Fable 5.2 FAQ

Short answers, built from the data on this page.

Claude Fable 5.2 is a model from Anthropic, released on Nov 9, 2026. Claude Fable 5.2 is Anthropic's latest Fable model, with a 1M-token context window, 128K max output and always-on adaptive thinking. It accepts text and images and returns text.

On the Respan gateway, Claude Fable 5.2 costs from $6.80 per 1M input tokens and $34.00 per 1M output tokens on Anthropic, after gateway discounts. Averaged across its 2 providers, it costs $7.40 per 1M input tokens and $37.00 per 1M output tokens.

Claude Fable 5.2 is available through 2 providers: Anthropic and Perplexity.

Claude Fable 5.2 accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "anthropic/claude-fable-5.2". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Claude Fable 5.2 scores 81.0 out of 100 on the Respan Index v1.1, ranking #1 of 169 models. By category: Coding 73.1, Agents 84.9, Reasoning 90.8, Knowledge & language 94.0, and Human preference 62.6. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Claude Fable 5.2 has 17 published benchmark scores, including Terminal-Bench Science 0.1 74.6%, APEX-Agents 80.1%, and SimpleBench 94.9%. Each score links to where it was published; the data is collected by Respan.