How much does the MiMo-V2.6-Flash API cost?

On FastMetal, MiMo-V2.6-Flash is billed per token in yen: ¥25.02 per 1M input tokens and ¥50.04 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call MiMo-V2.6-Flash with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "mimo-v2.6-flash" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of MiMo-V2.6-Flash?

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

What do I need to try MiMo-V2.6-Flash?

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

mimo-v2.6-flash

MiMo-V2.6-Flash

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

9/21/2026

1,048,576 tokens

Input: ¥25.018/M

Output: ¥50.036/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

video

audio

Output

text

Supported Parameters

frequency_penalty

include_reasoning

logit_bias

max_tokens

min_p

presence_penalty

reasoning

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_p

Max Output Tokens

131,072

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": "mimo-v2.6-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How MiMo-V2.6-Flash 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 'r's in 'strawberry' **Step 1: Write out each letter of the word individually:** `s - t - r - a - w - b - e - r - r - y` **Step 2: Go through each letter one by one and check if it's an 'r':** | Position | Letter | Is it 'r'? | Running Count | |----------|--------|------------|---------------| | 1 | s | ❌ | 0 | | 2 | t | ❌ | 0 | | 3 | **r** | ✅ | **1** | | 4 | a | ❌ | 1 | | 5 | w | ❌ | 1 | | 6 | b | ❌ | 1 | | 7 | e | ❌ | 1 | | 8 | **r** | ✅ | **2** | | 9 | **r** | ✅ | **3** | | 10 | y | ❌ | 3 | **Answer: There are 3 'r's in 'strawberry'.** 🍓 The first 'r' appears at position 3 (after "st"), and the remaining two are the double 'rr' near the end of the word.

6.5s response379 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…

## Cause of the Error The error occurs because the `users` prop is `undefined` when the component first renders. When you try to call `.map()` on `undefined`, it throws: ``` TypeError: Cannot read properties of undefined (reading 'map') ``` This typically happens when: 1. The **parent component** hasn't passed `users` yet (e.g., data is still loading from an API) 2. The prop name **doesn't match** between parent and child 3. The prop is **intentionally optional** but used unconditionally ## Fixes ### 1. Default parameter value (simplest fix) Set a default value for `users` so it's always an array: ```js function UserList({ users = [] }) { return ( <ul> {users.map(user =>…

7.6s response547 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` ## Issues Identified | Category | Issue | |----------|-------| | **Readability** | Imports inside function, vague names (`i`, `r`), no docstring/type hints | | **Performance** | Manual loop instead of list comprehension, no `requests.Session` (no connection reuse) | | **Best Practices** | Bare `except`, `== True`, silent failures, no backoff, no error propagation | --- ## Improved Version ```python import time import logging import requests from typing import Optional logger = logging.getLogger(__name__) def get_data( url: str, retries: int = 3, timeout: float = 10, backoff_factor: float = 2.0, ) -> Optional[list[dict]]: """ Fetch dat…

18.9s response1208 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the MiMo-V2.6-Flash API cost?: On FastMetal, MiMo-V2.6-Flash is billed per token in yen: ¥25.02 per 1M input tokens and ¥50.04 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call MiMo-V2.6-Flash with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "mimo-v2.6-flash" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of MiMo-V2.6-Flash?: 1,048,576 tokens, shared between the prompt and the response.
What do I need to try MiMo-V2.6-Flash?: 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.