MiniMax-Text-01.
MiniMax's first open MoE — 456B total, 45.9B active. 1M+ context via Lightning Attention.
1× Nvidia GB300.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
| Provider | Access | $/M in | $/M out | |
|---|---|---|---|---|
| Self-hosted on rented GPU cluster | self hosted | — | — | Run yourself → |
| Self-hosted on rented GPU cluster | self hosted | — | — | Run yourself → |
| MiniMax Platform | api direct | — | — | Launch ↗ |
| MiniMax Platform | api direct | — | — | Launch ↗ |
Frequently asked.
How do I run MiniMax-Text-01?
Where can I access MiniMax-Text-01?
How much does it cost to run MiniMax-Text-01?
Is MiniMax-Text-01 open-source or proprietary?
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
1152 GB | — | — | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
576 GB | — | — | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
288 GB | — | — | Compare → |
What it costs per month across providers.
Estimate your monthly bill for MiniMax-Text-01 across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
No priced API access rows on file for MiniMax-Text-01 yet.
Rent the GPU instead of paying per token.
For an open-weights model like MiniMax-Text-01, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month + your electricity rate × power draw.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
About MiniMax-Text-01.
MiniMax-Text-01 is MiniMax's debut open-weight Mixture-of-Experts model — 456B total parameters with 45.9B active per token. Notable for its 4M-token context window (achieved with Lightning Attention, a novel linear-attention hybrid architecture). MiniMax released it under their own community-friendly licence (commercial use allowed up to a usage threshold). Targets workloads where ultra-long context outweighs the cost of MoE inference.