How much does the Claude Sonnet 4.6 API cost?

On FastMetal, Claude Sonnet 4.6 is billed per token: $3.49 per 1M input tokens and $17.41 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 Sonnet 4.6 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-sonnet-4-6" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Claude Sonnet 4.6?

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

What do I need to try Claude Sonnet 4.6?

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-sonnet-4-6

Claude Sonnet 4.6

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

2/17/2026

1,000,000 tokens

Input: $3.49/M

Output: $17.41/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

Output

text

Supported Parameters

include_reasoning

max_tokens

reasoning

response_format

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_p

verbosity

Max Output Tokens

128,000

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)930ms

Throughput (p50)378 tokens/s

Measured through FastMetal's own gateway over the last 30 days (653 first-response samples).

Throughput is sampled once a day: the median of 26 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-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Claude Sonnet 4.6 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 the letter 'r' in 'strawberry' Let me go through the word letter by letter: | Position | Letter | Is it 'r'? | |----------|--------|------------| | 1 | s | No | | 2 | t | No | | 3 | r | ✅ Yes | | 4 | a | No | | 5 | w | No | | 6 | b | No | | 7 | e | No | | 8 | r | ✅ Yes | | 9 | r | ✅ Yes | | 10 | y | No | ## Result There are **3 r's** in 'strawberry'.

2.2s response181 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…

## Problem Analysis The error occurs because `users` is `undefined` when the component renders. You're calling `.map()` on `undefined`, which throws a `TypeError`. **Common causes:** - The prop isn't passed by the parent component - Data is still loading asynchronously when the component first renders - The parent passes `undefined` or a misspelled prop name --- ## Solutions ### Option 1: Default Parameter Value (Simplest Fix) ```javascript function UserList({ users = [] }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul> ); } ``` This assigns an empty array if `users` is `undefined`, so `.map()` always has an array to work with. --- ###…

9.4s response798 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 and Improvements ### Issues Identified 1. **Imports inside function** – should be at module level 2. **Bare `except`** – catches everything including `KeyboardInterrupt`, `SystemExit` 3. **`== True` comparison** – not Pythonic 4. **No logging/error visibility** – silent failures make debugging hard 5. **Magic numbers** – hardcoded `2`, `10` with no explanation 6. **No distinction between retriable/non-retriable errors** – e.g., 404 should not be retried 7. **Inefficient list building** – list comprehension is cleaner 8. **No exponential backoff** – fixed sleep is naive for real-world retry logic 9. **Missing type hints and docstring** --- ### Improved Version ```python im…

14.4s response1099 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Claude Sonnet 4.6 API cost?: On FastMetal, Claude Sonnet 4.6 is billed per token: $3.49 per 1M input tokens and $17.41 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 Sonnet 4.6 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-sonnet-4-6" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Claude Sonnet 4.6?: 1,000,000 tokens, shared between the prompt and the response.
What do I need to try Claude Sonnet 4.6?: 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.