Skip to contentLaunch price until December 31 · 45 days left

Claude Fable 5.2 API

AnthropicText, 1M context, answers up to 32K tokens

Claude for the hardest problems: deep reasoning and agents that work for hours. 1M tokens of context, OpenAI's chat format, pay per token.

1M tokensOur priceOfficialSaved
  • Input$4$8−50%
  • Output$20$40−50%
One callTikiAPIOfficial
  • A question500 tokens in, 300 out$0.008$0.016
  • A long chat10K in, 1K out$0.06$0.12
  • A document100K in, 2K out$0.44$0.88
  • A month of a busy bot50M in, 10M out$400.00$800.00

Official: Anthropic's price for Claude Fable 5.2, Claude API pricing, checked on Nov 14, 2026.

API

Call Claude Fable 5.2 in code.OpenAI's format: change the base URL and the key.

POST /v1/chat/completions

model
claude-fable-5.2
messages
The conversation: system, user and assistant turns, as in OpenAI's API. Text and images in user turns.
max_tokens
The longest answer, up to 32,000 tokens. 8,192 when not set.
stream
true for server-sent events as the answer is written.
…
temperature, tools, response_format and the rest go to the model as they are.
curl https://api.tikiapi.com/v1/chat/completions   -H "Authorization: Bearer $TIKIAPI_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "claude-fable-5.2",
    "messages": [
      {
        "role": "user",
        "content": "A train leaves at 9:40 and arrives at 13:05 after two 12-minute stops. What was its average moving speed over 214 km?"
      }
    ],
    "max_tokens": 1024
  }'

Overview

What Claude Fable 5.2 is good at.Anthropic's model for demanding reasoning and long-horizon agentic work.

  • Demanding reasoning

    Math, science and strategy that take many steps.

  • Long-horizon agents

    Keeps a goal through long chains of tool calls.

  • 1M-token context

    Everything the task needs in one call.

  • Pay per token

    Input and output priced per million. No plan.

Use cases

  • Research

    Questions that need many sources and careful checks.

  • Complex agents

    Multi-step work with tools, start to finish.

  • Analysis

    Plans, models and decisions with the reasoning laid out.

  • Hard code

    Architecture, migrations and tricky bugs.

FAQ

Claude Fable 5.2 API questions

Something else? Read the docs

How much does the Claude Fable 5.2 API cost?

$4 per million input tokens and $20 per million output tokens. A question of 500 tokens with a 300-token answer costs $0.008. No subscription, nothing upfront.

Does it work with the OpenAI SDK?

Yes. Point the SDK at https://api.tikiapi.com/v1, use your TikiAPI key and the model id claude-fable-5.2. The request and the answer have OpenAI's chat completions format, streaming included.

How long can an answer be?

Up to 32,000 tokens, set with max_tokens. Without it the answer is capped at 8,192 tokens.

What if a call fails?

It costs nothing. You pay for the tokens of an answer you get, never for an error.

Try Claude Fable 5.2 today.

No subscription. Pay per use.