How much does the Claude Fable 5.2 API cost?

On FastMetal, Claude Fable 5.2 is billed per token: $8.44 per 1M input tokens and $42.20 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Claude Fable 5.2 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-fable-5-2" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Claude Fable 5.2?

1,000,000 tokens, shared between the prompt and the response.

What do I need to try Claude Fable 5.2?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

Anthropic

anthropic-claude-fable-5-2

Claude Fable 5.2

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...

11/9/2026

1,000,000 tokens

Input: $8.44/M

Output: $42.20/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

file

Output

text

Supported Parameters

include_reasoning

max_completion_tokens

max_tokens

reasoning

reasoning_effort

response_format

stop

structured_outputs

tool_choice

tools

verbosity

Max Output Tokens

128,000

Reasoning Configuration

Default: Thinking on (effort: high)
Selectable effort levels: max
xhigh
high
medium
low
Turning thinking off: Not possible (always thinks)

How to control thinking, and what it costs

Data policy

Prompt retention: Unknown: we could not confirm
Training: Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "anthropic-claude-fable-5-2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Claude Fable 5.2 actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

**Step 1: Spell out the word letter by letter** | Position | Letter | Is it "r"? | |----------|--------|-----------| | 1 | s | No | | 2 | t | No | | 3 | **r** | Yes (1) | | 4 | a | No | | 5 | w | No | | 6 | b | No | | 7 | e | No | | 8 | **r** | Yes (2) | | 9 | **r** | Yes (3) | | 10 | y | No | **Step 2: Tally the matches** The letter "r" appears at positions 3, 8, and 9. **Step 3: Sanity check by syllable** - "straw" contains 1 r - "berry" contains 2 r's - 1 + 2 = 3 **Answer: There are 3 r's in "strawberry".**

6.5s response

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

## What's causing it `users` is `undefined` when `UserList` renders, so `users.map(...)` throws. This typically happens for one of these reasons: 1. **Data hasn't loaded yet.** The parent fetches users asynchronously, and on the first render the value is still `undefined`: ```jsx const [users, setUsers] = useState(); // undefined until fetch completes return <UserList users={users} />; ``` 2. **The prop isn't being passed or is misnamed**: ```jsx <UserList /> // no prop <UserList userList={data} /> // wrong prop name ``` 3. **The API response shape isn't what you expect**, for example passing `response.users` when the data is actually at `respons…

10.0s response

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

## Main issues **Correctness and robustness** 1. **Bare `except:`** catches everything, including `KeyboardInterrupt` and `SystemExit`. It also hides real bugs: a missing `"name"` key or invalid JSON is silently retried three times and then returns `[]`. 2. **Returning `[]` on failure is ambiguous.** The caller can't tell "no active items" from "the request failed". Raising an exception is safer. 3. **It retries errors that won't recover.** A 404 or 401 will fail the same way every time. Only transient failures (connection errors, timeouts, 429, 5xx) are worth retrying. 4. **It sleeps after the final attempt**, which wastes 2 seconds before giving up. **Readability and style** 5. **Impor…

30.0s response

Compare these answers side by side with other models →

Frequently asked questions

How much does the Claude Fable 5.2 API cost?: On FastMetal, Claude Fable 5.2 is billed per token: $8.44 per 1M input tokens and $42.20 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Claude Fable 5.2 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-fable-5-2" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Claude Fable 5.2?: 1,000,000 tokens, shared between the prompt and the response.
What do I need to try Claude Fable 5.2?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.