MiniMax: MiniMax M2
MiniMaxOpen weights
MiniMax: MiniMax M2 by MiniMax costs $0.26 per 1M input tokens and $1.02 per 1M output tokens, with a 205K-token context window.
Pricing
Input (per 1M tokens)
$0.26
Output (per 1M tokens)
$1.02
Cached input (per 1M)
—
| Provider | Input / 1M | Output / 1M |
|---|---|---|
| openrouter | $0.26 | $1.02 |
| MiniMax (minimax.io) | $0.30 | $1.20 |
Specifications
- Provider
- MiniMax
- Context window
- 205K tokens
- Parameters
- 229B
- Released
- Oct 2025
- Open weights
- Yes
- Frontier model
- No
- Hugging Face
- MiniMaxAI/MiniMax-M2
Benchmarks
- LMArena WebDev Elo
- 1296.9
Speed & latency
Time to first token
1.00s
Output speed
54 tok/s
Fastest host: minimax (via vercel-ai-gateway).
Compare MiniMax: MiniMax M2 with…
MiniMax: MiniMax M2 vs DeepSeek V3.1 Terminus$1.00/1MMiniMax: MiniMax M2 vs Qwen2.5 Coder 32B Instruct$1.00/1MMiniMax: MiniMax M2 vs Nemotron 3 Super 120B A12B$1.00/1MMiniMax: MiniMax M2 vs MiniMax M2.5$0.95/1MMiniMax: MiniMax M2 vs DeepSeek V3.1$0.95/1MMiniMax: MiniMax M2 vs Doubao-Seed-Code$1.12/1M
FAQ
How much does MiniMax: MiniMax M2 cost?
MiniMax: MiniMax M2 is priced at $0.26 per 1M input tokens and $1.02 per 1M output tokens. Output tokens cost more than input.
What is MiniMax: MiniMax M2's context window?
MiniMax: MiniMax M2 supports a context window of 205K tokens — the maximum prompt plus response length it can handle in a single request.
Is MiniMax: MiniMax M2 open weight?
Yes — MiniMax: MiniMax M2 has openly available weights.
Data as of 2026-10-15. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.