Back to Models
anthropic logo
anthropic/claude-fable-5

Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

6/9/2026
1,000,000 tokens
#1 Text (Overall)
Input: ¥1,787/M
Output: ¥8,935/M

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

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

How Claude Fable 5 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.

# Counting 'r's in "strawberry" Let me spell out the word letter by letter and check each one: | Position | Letter | Is it 'r'? | |----------|--------|------------| | 1 | s | No | | 2 | t | No | | 3 | **r** | ✅ Yes (1st) | | 4 | a | No | | 5 | w | No | | 6 | b | No | | 7 | e | No | | 8 | **r** | ✅ Yes (2nd) | | 9 | **r** | ✅ Yes (3rd) | | 10 | y | No | ## Reasoning breakdown: - The word "strawberry" can be split into two parts: **straw** + **berry** - "straw" contains one 'r': st**r**aw - "berry" contains two 'r's: be**rr**y (a double-r) ## Answer: **3** There are **three 'r's** in "strawberry."
39.6s response354 output tokens

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…

## Cause The error means that when `UserList` renders, the `users` prop is `undefined`, so calling `.map()` on it fails. This typically happens for one of these reasons: 1. **The parent isn't passing the prop** (or has a typo in the prop name): ```jsx <UserList /> // users is undefined <UserList user={users} /> // typo: "user" instead of "users" ``` 2. **Data is fetched asynchronously** — the component renders before the API call finishes, and the initial state is `undefined`: ```jsx const [users, setUsers] = useState(); // undefined initially! ``` ## Fixes **Option 1: Default parameter value** (quick fix) ```jsx function UserList({ users = [] }) { re…
51.3s response686 output tokens

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):…

# Code Review Your function works, but there are several issues worth addressing. Here's a breakdown by category: ## Issues Found ### 1. **Bare `except:` clause (critical)** This catches *everything*, including `KeyboardInterrupt`, `SystemExit`, and bugs like `KeyError` or `TypeError` in your own parsing code. You'll silently retry on programming errors and mask real problems. ### 2. **Imports inside the function** Imports belong at module level (PEP 8). Function-level imports add overhead on each call and hide dependencies. ### 3. **`== True` comparison** Use truthiness directly: `if item["active"]:` (PEP 8 explicitly recommends this). ### 4. **Silent failures** Returning `[]` on fail…
38.5s response1528 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Claude Fable 5 API cost?
On FastMetal, Claude Fable 5 is billed per token in yen: ¥1,787 per 1M input tokens and ¥8,935 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Claude Fable 5 with the OpenAI SDK?
Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-fable-5" 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?
1,000,000 tokens, shared between the prompt and the response.
How does Claude Fable 5 rank?
#1 on the public arena's Japanese board (ELO 1,526). Ranks move as the leaderboard is updated.
What do I need to try Claude Fable 5?
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.

Try Claude Fable 5 right now

Claude Fable 5 is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Leaderboard

Text
OverallELO: 1,507
#1
JapaneseELO: 1,526
#1
ChineseELO: 1,554
#3
KoreanELO: 1,501
#1
EnglishELO: 1,513
#2
frenchELO: 1,527
#1
germanELO: 1,491
#15
spanishELO: 1,518
#1
russianELO: 1,521
#1
CodingELO: 1,551
#3
MathELO: 1,529
#1
Creative WritingELO: 1,504
#1
Instruction FollowingELO: 1,512
#2
Hard PromptsELO: 1,533
#2
Multi-TurnELO: 1,515
#6
Vision
OverallELO: 1,313
#1
Code
OverallELO: 1,628
#10