MiniMax: MiniMax M3
minimax/minimax-m3MiniMax-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
Providers
14 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 DeepInfraus · fp8 | $0.28 | $1.10 | $0.06 | 1.38s | 18 tps | 100% |
| $0.30 | $1.20 | $0.06 | 1.51s | 77 tps | 99.95% | |
| $0.24 | $0.96 | $0.05 | 3.09s | 55 tps | 99.92% | |
| $0.30 | $1.20 | $0.06 | 0.82s | 96 tps | 99.91% | |
 ModelRun [by Modular]fp8 | $0.30 | $1.30 | $0.05 | 0.82s | 98 tps | 99.83% |
| $0.30 | $1.20 | $0.06 | 0.73s | 70 tps | 99.81% | |
| $0.30 | $1.20 | $0.06 | 1.16s | 80 tps | 99.29% | |
 CoreWeavefp4 | $0.23 | $0.96 | $0.05 | 0.51s | 98 tps | 98.34% |
| $0.30 | $1.20 | $0.06 | 3.15s | 55 tps | 98.32% | |
| $0.30 | $1.20 | $0.06 | 1.74s | 70 tps | 96.29% | |
| $0.30 | $1.20 | $0.06 | 1.09s | 72 tps | 95.55% | |
| $0.60 | $2.40 | $0.06 | 6.28s | 49 tps | 89.08% | |
| $0.60 | $2.40 | Variable | 3.25s | 96 tps | 73.08% | |
| DeepInfraus · fp8 | $0.22 | $0.88 | $0.04 | 5.97s | 25 tps | 67.44% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves MiniMax M3 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what MiniMax M3 costs pay-as-you-go elsewhere, not what you pay here.
Performance
Time to first token and output speed across every provider, over the last 3 days.
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Apps
Tools that most often run MiniMax M3, by tokens this week.
Activity
5704.5B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
