Skip to content
ShilpBot
AI Models

Anthropic Claude Fable 5.2: Pricing, Specs and Limits

Anthropic Claude Fable 5.2: most capable Claude model for demanding technical work, 1M context, 8.00 in / 40.00 out per 1M tokens. Specs, limits and test...

By ShilpBot Team · Published · 3 min read

Claude Fable 5.2 is described as Anthropic's most capable model, aimed at the most demanding technical work. The listing says it improves on Fable 5.1 in coding, reasoning and vision.

It is also the most expensive model on our list at $8 per million input tokens and $40 per million output tokens. That price makes it a specialist tool: worth it for hard problems, wasteful for routine ones.

Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

Anthropic Claude Fable 5.2 quick facts

DetailValue
DeveloperAnthropic
Model IDanthropic/claude-fable-5.2
Added to the catalogue2026-11-09
TypeMost capable Claude model for demanding technical work
ParametersNot listed
Context windowabout 1M tokens (1,000,000)
Maximum output128,000 tokens
Input typestext, image, file
Price8.00 in / 40.00 out per 1M tokens (cached input 0.20)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.

What Anthropic Claude Fable 5.2 is good for

  • Hard coding, reasoning and vision tasks where quality outweighs cost.
  • Reviewing complex code or documents where a mistake is expensive.
  • Long documents, with a 1M-token context window and file input.

Limits of Anthropic Claude Fable 5.2

  • It costs about 16 times as much per output token as Claude Haiku 5.5. Do not use it for simple tasks.
  • Cached input is much cheaper ($0.20 per million), so structure repeated prompts to use caching.
  • Output is capped at 128,000 tokens.

How Anthropic Claude Fable 5.2 compares

  • Anthropic Claude Sonnet 5.5: Both have a 1,000,000-token context window; both cap output at 128,000 tokens; it costs 8.00 input and 40.00 output per million tokens against 2.00 and 10.00.
  • Anthropic Claude Haiku 5.5: Both have a 1,000,000-token context window; both cap output at 128,000 tokens; it costs 8.00 input and 40.00 output per million tokens against 0.10 and 0.50.
  • OpenAI GPT-6.1 Sol: It has a smaller context window (1,000,000 against 1,050,000 tokens); both cap output at 128,000 tokens; it costs 8.00 input and 40.00 output per million tokens against 2.00 and 10.00.

Calling Anthropic Claude Fable 5.2 from code

Use the model ID anthropic/claude-fable-5.2 with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "anthropic/claude-fable-5.2", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what Anthropic Claude Fable 5.2 can do

  1. Give it a tricky concurrency bug and ask for the cause before any fix.
  2. Upload a complex diagram and ask it to explain the data flow.
  3. Run one hard task on Fable 5.2 and one on Sonnet 5.5 and decide whether the quality gap justifies the price.

What Anthropic Claude Fable 5.2 costs

The catalogue lists 8.00 per million input tokens and 40.00 per million output tokens, with cached input at 0.20 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 12.00. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $1.60 before caching. If your client reuses the same prompt prefix, cached input at 0.20 per million tokens can cut the input side of that bill by about 98 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.

Keep reading

Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

Is Claude Fable 5.2 worth the price?

Only for tasks where better quality saves real time or avoids costly mistakes. For everyday work a cheaper model such as Claude Sonnet 5.5 or Haiku 5.5 is usually more economical.

What are the cost and limits of Anthropic Claude Fable 5.2?

As of 2026-11-16 the catalogue lists 8.00 per million input tokens and 40.00 per million output tokens. About 1M tokens (1,000,000) context window, up to 128,000 output tokens, model ID anthropic/claude-fable-5.2. Prices can change, so check the live model page.

#Anthropic Claude Fable 5.2#Anthropic model#AI model pricing#AI API pricing#AI chat model#frontier model#OpenRouter