Minimax
100.00%Context205K
Max output205K
p50 latency946 ms
Throughput70.0 t/s
Input price$0.3
Output price$1.2
Model directory
Baseer model profileLanguage model
minimax/minimax-m2
MiniMax M2
MiniMax-M2 redefines efficiency for agents. It is a compact, fast, and cost-effective MoE model (230 billion total parameters with 10 billion active parameters) built for elite performance in coding and agentic tasks, all while maintaining powerful general intelligence.
Input / 1M tokens$0.3
Output / 1M tokens$1.2
Maximum context205K
Inference providers2
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Novita
100.00%Context204.8K
Max output131.1K
p50 latency1,284 ms
Throughput76.5 t/s
Input price$0.3
Output price$1.2
No training
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Minimax | 205K | 205K | 946 ms | 70.0 t/s | 100.000% | $0.3 | $1.2 | |
Novita | 204.8K | 131.1K | 1,284 ms | 76.5 t/s | 100.000% | $0.3 | $1.2 |
What can this model do?
Available modalities and capabilities across inference providers.
TextAdvanced reasoningTool useTools
Technical profile
- Model type
- Language model
- Release date
- Oct 27, 2025
- Knowledge cutoff
- 2024-10
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
minimax/minimax-m2Model profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.