MiniMax-M2 pricing
MiniMax-M2 API cost from MiniMax — $0.260 per 1M input tokens and $1.00 per 1M output tokens. Open weights. Estimate your real monthly bill below, then compare it against every other model.
Balanced open weights 200K context · all prices USD per 1M tokens, list price last verified 2026-06-27.
MiniMax-M2 capabilities & limits
Representative specs for this tier — confirm exact limits in the MiniMax docs.
Call MiniMax-M2 from your code
The exact model string and endpoint to use. Works with the OpenAI SDK — just point base_url at the URL below.
MiniMax-M2https://api.minimax.io/v1MINIMAX_API_KEYcurl https://api.minimax.io/v1/chat/completions \
-H "Authorization: Bearer $MINIMAX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "MiniMax-M2",
"messages": [{"role": "user", "content": "Hello"}]
}'Model strings follow each provider's naming convention; confirm the current id in the MiniMax docs before relying on it.
What a MiniMax-M2 API call actually costs
Blended input + output cost at MiniMax-M2's list rates — useful yardsticks before you commit to volume.
MiniMax-M2 cost calculator
Enter your monthly volume to estimate the MiniMax-M2 bill. Runs entirely in your browser.
MiniMax models — MiniMax-M2 in context
How MiniMax-M2 prices against its siblings. Cheapest reference cost first.
| Model | Input /1M | Output /1M | Cost / call* | Context | Type |
|---|---|---|---|---|---|
| MiniMax-M2 Open weights | $0.260 | $1.00 | $0.0013 | 200K | Balanced open |
| MiniMax-M3 Open weights, 1M context | $0.300 | $1.20 | $0.0015 | 1M | Flagship open |
*Reference cost of one call with 1,000 input + 1,000 output tokens — a neutral yardstick. Use the calculator for your real usage. Cheapest row highlighted.
How MiniMax-M2 pricing works
MiniMax-M2 is billed per token: a lower input price of $0.260 per million tokens for everything you send, and a higher output price of $1.00 per million for everything the model generates. To turn that into a real MiniMax-M2 bill, multiply by your monthly request volume and average prompt/response length — the calculator above does exactly that.
MiniMax-M2 does not list a separate cached-input rate, so every input token bills at $0.260 per million. If repeated context is a big part of your prompts, a model with prompt caching may end up cheaper in practice.
List prices move fast — always confirm the current numbers on the official MiniMax pricing page before relying on them for budgeting.
MiniMax-M2 pricing FAQ
How much does the MiniMax-M2 API cost?
MiniMax-M2 costs $0.260 per 1M input tokens and $1.00 per 1M output tokens. A typical 3K-input / 500-output call works out to about $0.0013.
What is MiniMax-M2's context window?
MiniMax-M2 has a 200K-token context window. Tokens you put in the prompt are billed at the $0.260 per 1M input rate.
Does MiniMax-M2 charge extra for output tokens?
Yes. Output (generated) tokens cost $1.00 per 1M, versus $0.260 per 1M for input — about 3.8× more, which is normal for LLM APIs.
Is there a cheaper alternative to MiniMax-M2?
In the same balanced tier, Command R (Cohere) is cheaper at $0.150 in / $0.600 out. The overall cheapest model on the market is Gemini 1.5 Flash-8B.
Is MiniMax-M2 open weights?
Yes — MiniMax-M2 is released as open weights, so you can self-host it instead of paying per-token API rates. The prices here are a representative hosted endpoint.