token.app › Compare › MiniMax M3.1 Flash vs Inkling Small
MiniMax M3.1 Flash vs Inkling Small
MiniMax M3.1 Flash is 2.4× cheaper per token on a blended 3:1 basis. MiniMax M3.1 Flash accepts the larger context window (1M).
Head to head
Blended price uses a 3:1 input:output mix
| MiniMax M3.1 Flash | Inkling Small | |
|---|---|---|
| Provider | MiniMax | Thinkingmachines |
| Input $/1M | $0.150 | $0.450 |
| Output $/1M | $0.600 | $1.20 |
| Blended $/1M | $0.262 | $0.637 |
| Context window | 1M | 524K |
| Max output | 524K | 262K |
| Released | Oct 2026 | Jul 2026 |
| Licence | Proprietary | Open weights |
Choose MiniMax M3.1 Flash if…
- Costs less per token — $0.262 vs $0.637 blended
- Larger context window (1M)
- Newer model (released Oct 2026)
Choose Inkling Small if…
- Open weights — self-hostable
FAQ
Which is better, MiniMax M3.1 Flash or Inkling Small?
We do not hold independently-run benchmark scores covering both MiniMax M3.1 Flash and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is MiniMax M3.1 Flash cheaper than Inkling Small?
MiniMax M3.1 Flash is cheaper: $0.262 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.150 vs $0.450. Output alone: $0.600 vs $1.20.
What context windows do MiniMax M3.1 Flash and Inkling Small have?
MiniMax M3.1 Flash: 1,000,000 tokens. Inkling Small: 524,288 tokens.
Who makes MiniMax M3.1 Flash and Inkling Small?
MiniMax M3.1 Flash is made by MiniMax. Inkling Small is made by Thinkingmachines.
Related comparisons