How much does the Kimi K2.6 API cost?

On FastMetal, Kimi K2.6 is billed per token in yen: ¥169.77 per 1M input tokens and ¥714.8 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Kimi K2.6 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "kimi-k2.6" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Kimi K2.6?

262,144 tokens, shared between the prompt and the response.

What do I need to try Kimi K2.6?

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

moonshotai/kimi-k2-6

Kimi K2.6

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

4/20/2026

262,144 tokens

Input: ¥169.765/M

Output: ¥714.8/M

Also on FastMetal: japan-kimi-k2.6 — Japan: Moonshot AI's Kimi K2.6 - hosted and run in Japan · Input: ¥64/M · Output: ¥316/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

Output

text

Supported Parameters

frequency_penalty

include_reasoning

logit_bias

logprobs

max_tokens

min_p

parallel_tool_calls

presence_penalty

reasoning

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_logprobs

top_p

Max Output Tokens

262,144

Reasoning Configuration

Default: Thinking on
Turning thinking off: Possible (reasoning.enabled: false)

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": "kimi-k2.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Kimi K2.6 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.

Here is the step-by-step count: **Step 1:** Write out the word and number each letter. 1. s 2. t 3. **r** ← 1st 'r' 4. a 5. w 6. b 7. e 8. **r** ← 2nd 'r' 9. **r** ← 3rd 'r' 10. y **Step 2:** Identify the positions containing the letter 'r'. - The 3rd letter is **r** - The 8th letter is **r** - The 9th letter is **r** **Step 3:** Tally the total. There are **3** letter 'r's in "strawberry".

4.5s response352 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…

The error occurs because `users` is `undefined` when your component renders. The `.map()` method only works on arrays, so calling it on `undefined` throws this error. This usually happens when: - The parent component hasn't finished fetching data yet - The `users` prop isn't being passed at all - The prop is misspelled in the parent component ## Quick Fix Set a **default value** for the `users` prop: ```jsx function UserList({ users = [] }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul> ); } ``` ## Alternative Fixes **Optional chaining** (renders nothing if undefined): ```jsx {users?.map(user => <li key={user.id}>{user.name}</li>)} ```…

71.8s response864 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):…

Here is a refactored version followed by a breakdown of the improvements. ### Refactored Function ```python import logging import time from typing import Any import requests logger = logging.getLogger(__name__) def fetch_active_items( url: str, *, retries: int = 3, timeout: float = 10.0, backoff: float = 2.0, ) -> list[dict[str, Any]]: """Fetch active items from an API endpoint with retry logic. Args: url: The API endpoint URL. retries: Number of retry attempts for transient failures. timeout: HTTP request timeout in seconds. backoff: Base delay in seconds between retries (linear backoff). Returns: A list of activ…

17.9s response4061 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Kimi K2.6 API cost?: On FastMetal, Kimi K2.6 is billed per token in yen: ¥169.77 per 1M input tokens and ¥714.8 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Kimi K2.6 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "kimi-k2.6" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Kimi K2.6?: 262,144 tokens, shared between the prompt and the response.
What do I need to try Kimi K2.6?: 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.