MiniMax: 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
In / Out Price
$0.30 / $1.20 per 1M
Context
1M
Released
May 31, 2026
Knowledge Cutoff
—
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 CoreWeavefp4 | 262K | $0.23 | $0.96 | $0.05 | — | — | 100.00% |
 GMICloudfp8 | 1M | $0.24 | $0.96 | $0.048 | — | — | 100.00% |
 DeepInfrafp8 | 524K | $0.28 | $1.10 | $0.056 | — | — | 100.00% |
 StreamLakefp8 | 1M | $0.30 | $1.20 | $0.06 | — | — | 100.00% |
 Venicefp8 | 524K | $0.30 | $1.20 | $0.06 | — | — | 96.67% |
 Together | 524K | $0.30 | $1.20 | $0.06 | — | — | 100.00% |
 Parasailfp8 | 1M | $0.30 | $1.20 | $0.06 | — | — | 100.00% |
 AtlasCloudfp8 | 524K | $0.30 | $1.20 | $0.06 | — | — | 89.29% |
 Novitafp8 | 1M | $0.30 | $1.20 | $0.06 | — | — | 100.00% |
| Minimaxfp8 | 524K | $0.30 | $1.20 | $0.06 | — | — | 100.00% |
 Mara | 1M | $0.60 | $2.40 | — | — | — | 100.00% |
 SambaNova | 1M | $0.60 | $2.40 | $0.06 | — | — | 100.00% |
 ModelRunfp4 | 1M | $0.75 | $3 | $0.15 | — | — | 100.00% |