Cheapest MiniMax M3 API providers

31 providers host MiniMax M3. The cheapest right now is CoreWeave at $0.23/MTok input and $0.96/MTok output. Prices below are pulled live from each provider, updated daily.

What would MiniMax M3 cost you?

CoreWeave is 69% cheaper than ModelRun at this workload.
Input tokens / month150M
Output tokens / month30M

Projected monthly cost = (input price × 150M) + (output price × 30M). Drag the sliders to match your actual workload; the chart re-ranks live.

#HostContextInput $/MTokOutput $/MTokBlendedUptime 30mQuant
1CoreWeave262k$0.23$0.96$0.3599.96%fp4
2CoreWeave262k$0.23$0.96$0.3599.85%fp4
3GMICloud1.0M$0.24$0.96$0.3699.47%fp8
4Morph256k$0.26$1.02$0.3887.55%fp4
5Morph256k$0.26$1.02$0.3894.65%fp4
6DeepInfra524k$0.28$1.10$0.4299.06%fp8
7DeepInfra524k$0.28$1.10$0.4299.44%fp8
8SiliconFlow1.0M$0.30$1.20$0.4597.96%fp8
9AtlasCloud524k$0.30$1.20$0.45100.00%fp8
10Parasail1.0M$0.30$1.20$0.4598.11%fp8
11Novita1M$0.30$1.20$0.4599.65%fp8
12StreamLake1M$0.30$1.20$0.4598.84%fp8
13Together524k$0.30$1.20$0.4599.92%
14Venice524k$0.30$1.20$0.45100.00%fp8
15Minimax524k$0.30$1.20$0.4599.90%fp8
16Fireworks AI$0.30$1.20$0.45
17AtlasCloud524k$0.30$1.20$0.4599.63%fp8
18Parasail1.0M$0.30$1.20$0.4598.79%fp8
19Novita1M$0.30$1.20$0.4599.80%fp8
20StreamLake1M$0.30$1.20$0.4599.24%fp8
21Together524k$0.30$1.20$0.4599.96%
22Venice524k$0.30$1.20$0.45100.00%fp8
23Minimax524k$0.30$1.20$0.4599.90%fp8
24TensorX$0.40$2.00$0.67
25Lyceum Technology$0.40$2.00$0.67
26SambaNova1.0M$0.60$2.40$0.9099.73%
27GMICloud1.0M$0.60$2.40$0.90100.00%fp8
28SambaNova1.0M$0.60$2.40$0.90100.00%
29Mara1.0M$0.60$2.40$0.90
30ModelRun1.0M$0.75$3.00$1.1399.77%fp4
31ModelRun1.0M$0.75$3.00$1.1399.11%fp4

Other rankings for MiniMax M3