MiniMax: MiniMax M3
MiniMaxOpen weights
MiniMax: MiniMax M3 by MiniMax costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 1M-token context window.
Pricing
Input (per 1M tokens)
$0.30
Output (per 1M tokens)
$1.20
Cached input (per 1M)
$0.06
| Provider | Input / 1M | Output / 1M |
|---|---|---|
| openrouter | $0.30 | $1.20 |
| MiniMax (minimax.io) | $0.30 | $1.20 |
Specifications
- Provider
- MiniMax
- Context window
- 1M tokens
- Parameters
- —
- Released
- Jun 2026
- Open weights
- Yes
- Frontier model
- No
- Hugging Face
- MiniMaxAI/Minimax-M3
Benchmarks
- GPQA Diamond
- 90.9
- LiveBench
- 67.3
- LMArena Vision Elo
- 1253.1
- LMArena WebDev Elo
- 1482.1
Speed & latency
Time to first token
0.87s
Output speed
175 tok/s
Fastest host: fireworks (via vercel-ai-gateway).
Compare MiniMax: MiniMax M3 with…
FAQ
How much does MiniMax: MiniMax M3 cost?
MiniMax: MiniMax M3 is priced at $0.30 per 1M input tokens and $1.20 per 1M output tokens. Output tokens cost more than input.
What is MiniMax: MiniMax M3's context window?
MiniMax: MiniMax M3 supports a context window of 1M tokens — the maximum prompt plus response length it can handle in a single request.
Is MiniMax: MiniMax M3 open weight?
Yes — MiniMax: MiniMax M3 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.