How much does the Claude Opus 4.8 API cost?

On FastMetal, Claude Opus 4.8 is billed per token: $5.28 per 1M input tokens and $26.38 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 Opus 4.8 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-opus-4-8" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Claude Opus 4.8?

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

What do I need to try Claude Opus 4.8?

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-opus-4-8

Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

5/27/2026

1,000,000 tokens

Input: $5.28/M

Output: $26.38/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 off
Selectable effort levels: max
xhigh
high
medium
low
Turning thinking off: Possible (reasoning.enabled: false)

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.

Measured performance

Time to first response (p50)1.5s

Throughput (p50)124 tokens/s

Measured through FastMetal's own gateway over the last 30 days (661 first-response samples).

Throughput is sampled once a day: the median of 27 observations over the last 30 days.

Time to first response is measured to the first streamed chunk; throughput counts all output tokens, including reasoning tokens. These are observations, not a performance guarantee.

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-4-8",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Claude Opus 4.8 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-by-step process: Let me go through each letter one at a time: | 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 | ## Answer: There are **3** 'r's in "strawberry". The three 'r's appear at positions 3, 8, and 9 — one after the "st" and two together in the "rry" ending.

4.5s response262 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 the Error The error tells you exactly what's happening: ``` TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) ``` At the moment `UserList` renders, the `users` prop is `undefined`, and you can't call `.map()` on `undefined`. This is extremely common when data is fetched asynchronously—the component renders **before** the data arrives. Common reasons `users` is undefined: - The parent hasn't passed the `users` prop at all - Data is still loading from an API (initial state is `undefined`) - The API response shape differs from what you expect (e.g. `data.users` vs `data`) --- # How to Fix It ## Option 1: De…

11.3s response761 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 Here's a breakdown of issues and suggested improvements for your function. ## Key Issues 1. **Imports inside the function** — should be at module level (runs on every call, harder to see dependencies). 2. **Bare `except:`** — catches everything, including `KeyboardInterrupt` and `SystemExit`. Silently swallowing errors makes debugging hard. 3. **Magic numbers** — `10`, `2`, `200` scattered around; extract as parameters/constants. 4. **`== True` comparison** — non-Pythonic; use the value directly (or `is True` if strict). 5. **Blocking `time.sleep(2)`** — fixed delay; exponential backoff is a better practice. 6. **`r.status_code == 200`** — misses other success codes; use `ra…

16.9s response1403 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Claude Opus 4.8 API cost?: On FastMetal, Claude Opus 4.8 is billed per token: $5.28 per 1M input tokens and $26.38 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 Opus 4.8 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-opus-4-8" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Claude Opus 4.8?: 1,000,000 tokens, shared between the prompt and the response.
What do I need to try Claude Opus 4.8?: 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.