MiniMax M3
minimax/minimax-m3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Modalities
Text
Image
Video
In / Out price
$0.30 / $1.20 per 1M
Context
1.05M · 512K out
Released
Jun 1, 2026
Providers
Live list prices and uptime across 13 providers serving this model.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output | Uptime 24h |
|---|---|---|---|---|---|---|
| CoreWeavefp4 | $0.23 | $0.96 | $0.05 | 262K | 236K | 99.77% |
| GMICloudfp8 | $0.24 | $0.96 | $0.048 | 1.05M | 524K | 99.72% |
| DeepInfrafp8 | $0.28 | $1.10 | $0.056 | 524K | 512K | 99.30% |
| StreamLakefp8 | $0.30 | $1.20 | $0.06 | 1M | 512K | 99.20% |
| Venicefp8 | $0.30 | $1.20 | $0.06 | 524K | 66K | 94.76% |
| Together | $0.30 | $1.20 | $0.06 | 524K | 472K | 99.91% |
| Parasailfp8 | $0.30 | $1.20 | $0.06 | 1.05M | 524K | 98.10% |
| AtlasCloudfp8 | $0.30 | $1.20 | $0.06 | 524K | 524K | 91.14% |
| Novitafp8 | $0.30 | $1.20 | $0.06 | 1M | 131K | 99.78% |
| Minimaxfp8 | $0.30 | $1.20 | $0.06 | 524K | 512K | 98.98% |
| Mara | $0.60 | $2.40 | — | 1.05M | 944K | 88.24% |
| SambaNova | $0.60 | $2.40 | — | 1.05M | 944K | 99.14% |
| ModelRunfp4 | $0.75 | $3.00 | $0.15 | 1.05M | 944K | 99.87% |
No implicit prompt caching; cache reads require explicit cache control.
Capabilities
Tool calling
Reasoning
Frequency penalty
Include reasoning
Logit bias
Logprobs
Max tokens
Min p
Presence penalty
Repetition penalty
Response format
Seed
Stop
Structured outputs
Temperature
Tool choice
Top K
Top logprobs
Top P
Pricing detail
- Input
- $0.30
- Output
- $1.20
- Cache read
- $0.06
- Cache write
- —
USD per 1M tokens.