Fireworks
100.00%Context512K
Max output512K
p50 latency1,055 ms
Throughput154.0 t/s
Input price$0.3
Output price$1.2
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
minimax/minimax-m3
MiniMax M3
MiniMax-M3 is a frontier-class foundation model that unites the three capabilities defining today's frontier: a 1M-token context window, frontier coding and agentic performance, and native multimodality — the first open-weight model to deliver all three in a single system.
Input / 1M tokens$0.255
Output / 1M tokens$1.02
Maximum context1M
Inference providers5
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.
Gmicloud
98.64%Context1M
Max output1M
p50 latency875 ms
Throughput—
Input price$0.6
Output price$2.4
Caching
Minimax
99.43%Context1M
Max output1M
p50 latency1,069 ms
Throughput101.0 t/s
Input price$0.3
Output price$1.2
Caching
Morph
100.00%Context256K
Max output256K
p50 latency1,145 ms
Throughput94.0 t/s
Input price$0.255
Output price$1.02
Zero retentionNo trainingCaching
Nebius
99.94%Context1M
Max output1M
p50 latency905 ms
Throughput284.0 t/s
Input price$0.3
Output price$1.2
Zero retentionNo trainingCaching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Fireworks | 512K | 512K | 1,055 ms | 154.0 t/s | 99.999% | $0.3 | $1.2 | |
Gmicloud | 1M | 1M | 875 ms | — | 98.645% | $0.6 | $2.4 | |
Minimax | 1M | 1M | 1,069 ms | 101.0 t/s | 99.427% | $0.3 | $1.2 | |
Morph | 256K | 256K | 1,145 ms | 94.0 t/s | 100.000% | $0.255 | $1.02 | |
Nebius | 1M | 1M | 905 ms | 284.0 t/s | 99.944% | $0.3 | $1.2 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageAdvanced reasoningTool useVisionAutomatic cachingFile inputTools
Technical profile
- Model type
- Language model
- Release date
- May 31, 2026
- Knowledge cutoff
- —
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
minimax/minimax-m3Model profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.