How much does the Claude Opus 5.5 API cost?

On FastMetal, Claude Opus 5.5 is billed per token in yen: ¥692.4 per 1M input tokens and ¥3,462 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Claude Opus 5.5 with the OpenAI SDK?

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

What is the context window of Claude Opus 5.5?

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

What do I need to try Claude Opus 5.5?

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.

Back to Models

anthropic-claude-opus-5-5

Claude Opus 5.5

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...

9/22/2026

1,000,000 tokens

Input: ¥692.4/M

Output: ¥3,462/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

temperature

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-opus-5-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Claude Opus 5.5 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" **Step 1: Spell out the word letter by letter.** | Position | Letter | |----------|--------| | 1 | s | | 2 | t | | 3 | **r** ← | | 4 | a | | 5 | w | | 6 | b | | 7 | e | | 8 | **r** ← | | 9 | **r** ← | | 10 | y | **Step 2: Mark each 'r'.** - Position 3: the "r" in "st**r**aw" - Positions 8 and 9: the double "rr" in "be**rr**y" **Step 3: Add them up.** 1 (in "straw") + 2 (in "berry") = **3** **Answer: There are 3 'r's in "strawberry."** A common mistake is to count only 2, because the double "rr" in "berry" can be read as a single sound. Breaking the word into its parts, "straw" + "berry," makes all three easy to see.

5.4s response376 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…

## What's causing it The error means `users` is `undefined` when `UserList` renders, so `users.map(...)` fails. The component itself is fine. The problem is the value it receives from its parent. Common reasons: 1. **Async data hasn't loaded yet.** This is the most common cause. The parent fetches users from an API, and on the first render the state is still `undefined`: ```jsx const [users, setUsers] = useState(); // undefined on first render useEffect(() => { fetch('/api/users').then(r => r.json()).then(setUsers); }, []); return <UserList users={users} />; // crashes before fetch completes ``` 2. **The prop isn't being passed**, or has a different name: ```js…

10.9s response1040 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: `get_data` The function works in the happy path, but it has several issues that can hide bugs, waste time, and make failures hard to diagnose. ## Issues ### 🔴 Correctness and Reliability **1. The bare `except:` is the most serious problem.** It catches everything, including `KeyboardInterrupt`, `SystemExit`, and bugs in your own code. For example, if an item is missing the `"name"` key, the resulting `KeyError` gets swallowed and the request is retried as if it were a network error. The same happens with invalid JSON. Catch only the exceptions you expect, such as `requests.ConnectionError` and `requests.Timeout`. **2. Failure is indistinguishable from "no results."** Ret…

33.5s response4023 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Claude Opus 5.5 API cost?: On FastMetal, Claude Opus 5.5 is billed per token in yen: ¥692.4 per 1M input tokens and ¥3,462 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Claude Opus 5.5 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-opus-5-5" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Claude Opus 5.5?: 1,000,000 tokens, shared between the prompt and the response.
What do I need to try Claude Opus 5.5?: 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.