MiniMaxPaidOperational
Minimax M3
API model name: minimax-m3
Minimax M3 is MiniMax's chat model, served on the Api.Airforce unified API. Capabilities include Prompt caching. It is priced at $0.50 per million input tokens and $1.00 per million output tokens. Access it through the OpenAI-compatible API with one key, alongside 65+ other models on Api.Airforce.
Pricing
Pricing by input length
| Input length | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| <512K | $0.50 | $1.00 |
| ≥512K | $1.00 | $4.00 |
Specifications
- Provider
- MiniMax
- Type
- chat model
- Prompt caching
- Supported
Capabilities
Prompt cachingStreaming
Related models
Minimax M2.5MiniMax · FreeMinimax M2.7MiniMax · $0.38 / 1MGlm 4.7Zai · $0.70 / 1MGlm 4.7 FlashZai · FreeGlm 4.7 FreeZai · FreeGlm 5Zai · $0.80 / 1MGlm 5 FreeZai · FreeGlm 5.1Zai · $0.80 / 1MGpt 4o MiniOpenAI · FreeGpt 5.1 Codex MiniOpenAI · $0.18 / 1MGpt 5.3 CodexOpenAI · $0.75 / 1MGpt 5.4OpenAI · $1.25 / 1M
Loading live metrics…
Loading live metrics…
Use Minimax M3 via the API
OpenAI-compatible — point any OpenAI SDK at https://api.airforce/v1 and pass minimax-m3 as the model.
cURL
curl https://api.airforce/v1/chat/completions \
-H "Authorization: Bearer $AIRFORCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-m3",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Python
from openai import OpenAI
client = OpenAI(base_url="https://api.airforce/v1", api_key="$AIRFORCE_API_KEY")
r = client.chat.completions.create(
model="minimax-m3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airforce/v1", apiKey: process.env.AIRFORCE_API_KEY });
const r = await client.chat.completions.create({
model: "minimax-m3",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);