MiniMax M2.7
$0.3
Input / MTok
$1.2
Output / MTok
$0.06
Cache read / MTok
Hosted third-party inference; price is Fireworks' Standard serverless rate, not MiniMax's own API. Optional Priority tier at 1.5x.
API identifier accounts/fireworks/models/minimax-m2p7
· vendor pricing page
Full price sheet
| Metric | USD / million tokens |
|---|---|
| Input | $0.3 |
| Output | $1.2 |
| Cache read | $0.06 |
Price history
| Observed | Metric | Price |
|---|---|---|
| 2026-08-08 07:26:49 | Input | $0.3 |
| 2026-08-08 07:26:49 | Output | $1.2 |
| 2026-08-08 07:26:49 | Cache read | $0.06 |
Current prices are free and always will be. The full series — every observation since we started watching, which nobody can reconstruct after the fact — is the part Pro pays for.
Changes affecting this model
coverage
MiniMax M2.7 added to coverage
—
2026-08-08Compare with
Models at a similar price point.
| Model | Input | Output | |
|---|---|---|---|
| MiniMax M3 | $0.3 | $1.2 | compare → |
| MiniMax M3 | $0.3 | $1.2 | compare → |
| GPT-5.4 nano | $0.2 | $1.25 | compare → |
| GPT-5.6 Luna | $0.2 | $1.2 | compare → |
| Inkling Small | $0.5 | $1.2 | compare → |
| Llama 3.3 70B Instruct Turbo | $1.04 | $1.04 | compare → |