How much does the Kimi K3.1 Pro API cost?

On FastMetal, Kimi K3.1 Pro is billed per token: $2.11 per 1M input tokens and $10.55 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 Kimi K3.1 Pro with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "kimi-k3.1-pro" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Kimi K3.1 Pro?

1,048,576 tokens, shared between the prompt and the response.

What do I need to try Kimi K3.1 Pro?

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

Moonshot

kimi-k3.1-pro

Kimi K3.1 Pro

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

10/23/2026

1,048,576 tokens

Input: $2.11/M

Output: $10.55/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

video

Output

text

Supported Parameters

frequency_penalty

include_reasoning

logprobs

max_tokens

presence_penalty

reasoning

reasoning_effort

response_format

stop

structured_outputs

tool_choice

tools

top_logprobs

Max Output Tokens

943,718

Reasoning Configuration

Default: Thinking on (effort: max)
Selectable effort levels: max
high
low
none
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: Unknown — not declared

"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": "kimi-k3.1-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Kimi K3.1 Pro 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.

There are **3** ‘r’s in **“strawberry.”** 1. Write out each letter: **s – t – r – a – w – b – e – r – r – y** 2. Locate the ‘r’s: positions **3, 8, and 9**. 3. Count them: **1 + 1 + 1 = 3**.

11.3s 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 the error The error means `users` is `undefined` when the component renders, and you can't call `.map()` on `undefined`. The component itself is fine — the problem is that whatever renders `<UserList />` either isn't passing the prop, or is passing a value that isn't an array yet. The most common cause is **async data fetching**: the parent renders `UserList` before the data has loaded. ```jsx function App() { const [users, setUsers] = useState(); // ❌ undefined on first render useEffect(() => { fetch('/api/users') .then(res => res.json()) .then(setUsers); }, []); return <UserList users={users} />; // users is undefined here initially } ``` On…

36.3s 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):…

The timeout and bounded retry loop are good starting points. The biggest issue is that failures—and even programming errors—are silently converted into retries and then `[]`. ### Suggested improvements - **Avoid bare `except:`**. It catches `KeyboardInterrupt`, `KeyError`, JSON/schema errors, and other bugs. Retry only expected transient network failures; let malformed responses fail visibly. - **Use a deliberate retry policy**. Retrying `401`, `403`, or `404` usually wastes time. Retry only transient statuses, use exponential backoff, and avoid sleeping after the final attempt. - **Do not use `[]` for both failure and no results**. Prefer raising the final exception so callers can disting…

560.2s response

Compare these answers side by side with other models →

Frequently asked questions

How much does the Kimi K3.1 Pro API cost?: On FastMetal, Kimi K3.1 Pro is billed per token: $2.11 per 1M input tokens and $10.55 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 Kimi K3.1 Pro with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "kimi-k3.1-pro" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Kimi K3.1 Pro?: 1,048,576 tokens, shared between the prompt and the response.
What do I need to try Kimi K3.1 Pro?: 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.