MiniMax: MiniMax M2
minimax/minimax-m2
MiniMax M2 is MiniMax's budget option at $0.255/$1.02 per million input/output tokens, with a 204K-token context. It sits mid-board on capability, at #144 of 262 on the TryAii Score — its best showing is #36 on IFBench. It's among the fastest models we track, at roughly 90-130 tokens/sec.
Prompt $/1M
$0.255
Completion $/1M
$1.020
Context
204,800 tok
Best provider
150 tok/s · Google
Specs
- Model id
- minimax/minimax-m2
- Display name
- MiniMax: MiniMax M2
- Modality
- text->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 204,800
- Max completion
- 131,072
- Prompt $/1M
- $0.255
- Completion $/1M
- $1.020
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Googlefastest | 150 |
| Minimax | 70 |