minimax/minimax-m2.5
196,608 context · $0.30/M input tokens · $1.20/M output tokens
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
Harga
Bayar sesuai pemakaian
Tanpa biaya di muka, bayar hanya sesuai penggunaan
Coba model
Penggunaan API
Gunakan contoh kode berikut untuk integrasi dengan API kami:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="minimax/minimax-m2.5",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)Pengenalan Model
Minimax minimax-m2.5
MiniMax-M2
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity, excelling in coding, office work, and agentic workflows.
Why It Looks Great
- MoE (Mixture of Experts) architecture for efficient processing
- 204800 context window for long document handling
- Competitive pricing at $0.3/$1.2 per million tokens
Key Features
- Context Window: 204800 tokens
- Max Output: N/A tokens
- Vision: Supported
- Function Calling: Supported
Specifications
| Specification | Value |
|---|---|
| Provider | Minimax |
| Model Type | Large Language Model (LLM) |
| Architecture | MoE (Mixture of Experts) |
| Context Window | 204800 tokens |
| Max Output | tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
Pricing
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.3 |
| Output | $1.2 |
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- Submit — the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: minimax/minimax-m2.5
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="minimax/minimax-m2.5",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "minimax/minimax-m2.5",
"messages": [{"role": "user", "content": "Hello!"}]
}'Notes
- Model: minimax/minimax-m2.5
- Provider: Minimax
Info
Fitur yang Didukung
Panduan Akses API
Minimax M2.5 API
minimax/minimax-m2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
Input
$0.3 /M
Output
$1.2 /M
Konteks
197K
Output Maks.
66K
Penggunaan Tool
Didukung
Coba Minimax M2.5 di WaveSpeedAI
Akses Minimax M2.5 melalui API terpadu kami — kompatibel dengan OpenAI, tanpa cold start, harga transparan.
Pertanyaan Umum tentang Minimax M2.5
Berapa biaya Minimax M2.5 melalui API?+
Harga di WaveSpeedAI: $0.30 per juta token input dan $1.20 per juta token output. Prompt caching dan batch processing ditagih terpisah dan mengurangi biaya efektif pada beban kerja yang panjang dan berulang.
Berapa context window Minimax M2.5?+
Minimax M2.5 mendukung hingga 197K token konteks dengan hingga 66K token output per permintaan.
Apakah Minimax M2.5 kompatibel dengan OpenAI?+
Ya. WaveSpeedAI menyediakan Minimax M2.5 melalui endpoint yang kompatibel dengan OpenAI di https://llm.wavespeed.ai/v1. Arahkan OpenAI SDK resmi ke base URL ini dengan API key WaveSpeedAI Anda — tanpa perubahan kode lainnya.
Bagaimana memulai dengan Minimax M2.5?+
Masuk ke WaveSpeedAI, buat API key di Access Keys, lalu kirim permintaan ke https://llm.wavespeed.ai/v1/chat/completions dengan model id seperti ditampilkan di atas. Akun baru menerima kredit gratis untuk menguji Minimax M2.5.