MiniMax-M2.1: GPU memory and hosting cost
Open weights · 228.69 billion parameters · Mixture of experts · 196,608-token context · licence other
No cloud sells this model per token: to use it you run it yourself, on GPU instances you rent.
Run it yourself
It needs 285.9 GB of GPU memory at fp8, the precision it ships in.
| Cloud | Cheapest instance that fits | GPUs | An hour | A month, around the clock |
|---|---|---|---|---|
| Nebius | gpu-b300-sxm.1gpu-24vcpu-346gb | 1 × B300 288 GB | $9.50 | $6,935 |
| Fireworks AI | b300.1x | 1 × B300 288 GB | $15.00 | $10,950 |
| Crusoe | a100-sxm.8x | 8 × A100 80 GB | $18.40 | $13,432 |
| Google Cloud | a2-ultragpu-4g | 4 × A100 80 GB | $20.28 | $14,801 |
| AWS | p4d.24xlarge | 8 × A100 40 GB | $21.96 | $16,029 |
| Azure | Standard_ND96asr_v4 | 8 × A100 40 GB | $27.20 | $19,854 |
| Alibaba Cloud | ecs.gn8v-4x.8xlarge | 4 × GPU H 96 GB | $29.25 | $21,349 |
| Together AI | hgx-h100.8gpu | 8 × H100 80 GB | $31.92 | $23,302 |
| OCI | BM.GPU.A100-v2.8 | 8 × A100 80 GB | $32.00 | $23,360 |
More from MiniMax
Similar size, open weights
- OpenAI gpt-oss 120B
- GLM 5.3 Flash
- Llama 4 Maverick 17B
- DeepSeek V4 Flash
- DeepSeek V4 Flash 0731
- Qwen3 235B A22B Instruct 2507
List prices collected 4 November 2026, refreshed every three hours. No negotiated rates or taxes.