MiniMax M3 Preview API
minimax/minimax-m3-preview
Call MiniMax M3 Preview through UberLLM’s OpenAI-compatible API — from $0.1650/M input and $0.6600/M output, routed automatically to the cheapest healthy seller. MiniMax · 524,288 token context. Fee included.
MiniMax M3 Preview pricing
- Input
- $0.165
- Output
- $0.66
- Cached input
- $0.033
- Input
- $0.33
- Output
- $1.32
- Cached input
- $0.066
| Provider | Input | Output | Cached input |
|---|---|---|---|
| Venice AI | $0.30 | $1.20 | $0.06 |
UberLLM routes every request to the cheapest healthy seller for this model. The price shown includes UberLLM’s 10% fee.
How to use MiniMax M3 Preview with the OpenAI SDK
Already using the OpenAI SDK? Change one line — the base URL — and call MiniMax M3 Preview with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uberllm.dev/v1",
api_key="ull_your_key_here",
)
resp = client.chat.completions.create(
model="minimax/minimax-m3-preview",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)MiniMax M3 Preview API — FAQ
How much does the MiniMax M3 Preview API cost?
MiniMax M3 Preview is listed from $0.1650 per million input tokens and $0.6600 per million output tokens through UberLLM, which routes each request to the cheapest healthy seller on a live marketplace and bills the price shown, which includes UberLLM's 10% fee.
How do I call MiniMax M3 Preview via API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "minimax/minimax-m3-preview". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.
Is MiniMax M3 Preview OpenAI-compatible on UberLLM?
Yes. Every model on UberLLM — including MiniMax M3 Preview — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.