xiaomi/mimo-v2.5-pro
Дата выпуска: 2026-04-23
1,048,576 context · $1.00/M input tokens · $3.00/M output tokens
MiMo-V2.5-Pro is Xiaomi’s flagship open model for advanced agentic workflows, complex software engineering, and long-horizon task execution. Built on a sparse Mixture-of-Experts architecture with 1.02T total parameters and 42B active parameters, it supports a 1M-token context window and is optimized for autonomous coding agents, large codebase reasoning, tool-use workflows, and multi-step problem solving. It delivers strong performance on agentic and software engineering benchmarks such as ClawEval, GDPVal, and SWE-bench Pro, with an emphasis on token-efficient long-context execution.
Оплата по факту использования
Никаких авансовых платежей — платите только за то, чем пользуетесь
Используйте следующие примеры кода для интеграции с нашим API:
import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'xiaomi/mimo-v2.5-pro',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'xiaomi/mimo-v2.5-pro',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}MiMo-V2.5-Pro is Xiaomi’s flagship open model for advanced agentic workflows, complex software engineering, and long-horizon task execution. Built on a sparse Mixture-of-Experts architecture with 1.02T total parameters and 42B active parameters, it is optimized for autonomous coding agents, large codebase reasoning, tool use, and multi-step problem solving.
| Specification | Value |
|---|---|
| Provider | xiaomi |
| Model Type | Chat Completions model |
| Architecture | Sparse Mixture-of-Experts |
| Parameters | 1.02T total / 42B active |
| Context Window | 1,048,576 tokens |
| Max Input | 1,032,192 tokens |
| Max Output | 16,384 tokens |
| Input | Text |
| Output | Text |
| Vision | Not listed |
| Function Calling | Supported |
| Structured Outputs | Supported |
| Primary Use Cases | Agentic coding, complex software engineering, long-horizon tasks, tool use |
| Token Type | Cost |
|---|---|
| Input | $1.00 per million tokens |
| Output | $3.00 per million tokens |
| Cached Input | $0.20 per million tokens |
Base URL: https://llm.wavespeed.ai/v1
API Endpoint: chat/completions
Model ID: xiaomi/mimo-v2.5-pro
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="xiaomi/mimo-v2.5-pro",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "xiaomi/mimo-v2.5-pro",
"messages": [{"role": "user", "content": "Hello!"}]
}'xiaomi/mimo-v2.5-pro
MiMo-V2.5-Pro is Xiaomi’s flagship open model for advanced agentic workflows, complex software engineering, and long-horizon task execution. Built on a sparse Mixture-of-Experts architecture with 1.02T total parameters and 42B active parameters, it supports a 1M-token context window and is optimized for autonomous coding agents, large codebase reasoning, tool-use workflows, and multi-step problem solving. It delivers strong performance on agentic and software engineering benchmarks such as ClawEval, GDPVal, and SWE-bench Pro, with an emphasis on token-efficient long-context execution.
Ввод
$1 /M
Вывод
$3 /M
Контекст
1049K
Макс. вывод
16K
Использование инструментов
Поддерживается
Доступ к Mimo V2.5 Pro через наш единый API — совместимость с OpenAI, без холодных стартов, прозрачные цены.
Цены на WaveSpeedAI: $1.00 за миллион входных токенов и $3.00 за миллион выходных токенов. Prompt caching и batch processing тарифицируются отдельно и снижают эффективную стоимость длинных повторяющихся нагрузок.
Mimo V2.5 Pro поддерживает до 1049K токенов контекста и до 16K токенов вывода на запрос.
WaveSpeedAI предоставляет Mimo V2.5 Pro по адресу https://llm.wavespeed.ai/v1 через интерфейс Chat Completions, совместимый с OpenAI. В большинстве клиентов OpenAI SDK достаточно изменить base URL и API-ключ; необязательные поля зависят от модели.
Войдите в WaveSpeedAI, создайте API-ключ в Access Keys и отправьте запрос на https://llm.wavespeed.ai/v1/chat/completions с указанным выше model id. Актуальные доступность, возможности и цены смотрите в каталоге моделей.