Anthropic

Claude Fable 5 2

Anthropic's top tier for the most demanding technical work: a 1M-token context window, always-on adaptive extended thinking (high by default, up to max), and up to 30% faster output than Fable 5.1. Best suited to open-ended problems without a known solution, such as large-scale code migrations, cross-file engineering changes, and hard research or math, where long-running autonomous work pays off. For everyday coding and knowledge tasks Anthropic still recommends starting with Opus 5.5. At $8/M input and $40/M output tokens, cost is the main reason to reserve it for genuinely hard problems instead of using it as the default.

  • Reasoning
  • Tool use
  • Structured output
  • Long context

AI Chat

Send a prompt and see the response here.

claude-fable-5-2
Current conversation
How can I help you?

Start a conversation with this model and ask follow-up questions.

Uses your account balance at the model’s current rates.

USD /1M tokens

Pricing

GroupInputOutputCache ReadCache Write
default$8$40$0.2$16
claude-0.34$2.72$13.6$0.068$5.44
default
Input$8Output$40Cache Read$0.2Cache Write$16
claude-0.34
Input$2.72Output$13.6Cache Read$0.068Cache Write$5.44

Public list prices are shown in USD. Final charges may vary by account group and usage tier.

API

Code examples

curl --location --request POST 'https://api.tokenhot.ai/v1/messages' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "claude-fable-5-2",
    "messages": [
        {
            "role": "user",
            "content": "What can you do?"
        }
    ],
    "max_tokens": 100
}'

Anthropic

Related models

ClaudeAnthropicClaude Opus 4 8

Anthropic current Opus flagship for the most demanding reasoning, long-running agents, and high-autonomy coding. It supports a 1M-token context window and adaptive thinking; choose it when quality and reliability matter more than latency or cost.

$1.7/1M tokensClaudeAnthropicClaude Sonnet 4 6

The Claude lineup workhorse, balancing strong intelligence, response speed, and cost. It supports a 1M-token context window and adaptive thinking, making it a strong starting point for coding, document analysis, data work, and tool-using agents; move to Opus for the most complex tasks.

$1.02/1M tokensClaudeAnthropicClaude Opus 5

A premium model for complex agentic coding and enterprise knowledge work, emphasizing long-horizon planning, sustained execution, self-checking, and reliable delivery. With a million-token context window, it is suited to large codebases, complex documents, and multi-step projects that need limited human oversight.

$1.7/1M tokensClaudeAnthropicClaude Fable 5 1

A flagship long-context model for demanding, long-running knowledge work, coding projects, and multi-step agentic tasks. It accepts text, images, and PDFs, making it a strong fit for cross-file analysis, complex research, and sustained tool use. It prioritizes reasoning depth and long-horizon execution over speed and cost, so it is best reserved for tasks where reliable completion matters.

$3.4/1M tokens

FAQ

Frequently asked questions

What is Claude Fable 5 2 best suited for?

Claude Fable 5 2 is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.

How is Claude Fable 5 2 priced?

Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.

How can I call Claude Fable 5 2?

Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.

Get started

Build with Claude Fable 5 2

Use in Console