MiniMax M2.7
The cheapest provider for MiniMax M2.7 is GMICloud at $0.368 per 1M tokens (blended), charging $0.21 per 1M input and $0.84 per 1M output tokens. 6 providers serve it; the most expensive charges 2.9× as much. Context window: 200K tokens. Prices tracked since Oct 3, 2026.
Best price
$0.368
at GMICloud
Input / output
$0.21 / $0.84
per 1M tokens
Providers
6
2.9× spread
7 days
—
best price
30 days
—
best price
Context
200K
tokens
Providers
Active offers ranked by blended price. Bars are relative to the most expensive.
| Provider | Input | Output | Blended | vs cheapest | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
GMICloudCheapest fp8·−30% discount | $0.21 | $0.84 | $0.368 | best | |||
| fp8·−10% discount | $0.27 | $1.08 | $0.473 | +29% | |||
| fp8 | $0.30 | $1.20 | $0.525 | +43% | |||
| fp8 | $0.30 | $1.20 | $0.525 | +43% | |||
| $0.60 | $1.80 | $0.90 | +145% | ||||
Minimaxhighspeed fp8 | $0.60 | $2.40 | $1.05 | +186% | |||
| $0.60 | $2.40 | $1.05 | +186% |
- GMICloudCheapest$0.368$0.21 in · $0.84 outbest192K ctx99.8% uptimefp8·−30% discount
- $0.473$0.27 in · $1.08 out+29%200K ctx99.5% uptimefp8·−10% discount
- $0.525$0.30 in · $1.20 out+43%192K ctx99.1% uptimefp8
- $0.525$0.30 in · $1.20 out+43%200K ctx99.7% uptimefp8
- $0.90$0.60 in · $1.80 out+145%192K ctx94.4% uptime
- highspeed$1.05$0.60 in · $2.40 out+186%200K ctx98.8% uptimefp8
- $1.05$0.60 in · $2.40 out+186%192K ctx0.0% uptime
Blended = (3 × input + output) / 4.
Price history
Hover to compare providers at any point in time. Click a legend item to hide it.
USD per 1M tokens · each step is a price change
Not enough history yet
Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.
Other pricing
Cache, reasoning and per-call fees. Token rates per 1M; others per unit.
| Offered by | Cache read |
|---|---|
| GMICloud | $0.042 |
| Novita | $0.054 |
| AtlasCloud, Minimax +2 | $0.06 |
Change log
Every recorded change for this model since Oct 3, 2026.
No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.
About this model
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
- Released
- Mar 18, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- minimax/minimax-m2.7-20260318
- Weights
- MiniMaxAI/MiniMax-M2.7