token.app › Compare › MiniMax M3 vs Inkling Small
MiniMax M3 vs Inkling Small
MiniMax M3 and Inkling Small split the 2 shared benchmarks evenly. MiniMax M3 is 1.2× cheaper per token on a blended 3:1 basis. MiniMax M3 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| MiniMax M3 | Inkling Small | |
|---|---|---|
| Provider | MiniMax | Thinkingmachines |
| Input $/1M | $0.300 | $0.450 |
| Output $/1M | $1.20 | $1.20 |
| Blended $/1M | $0.525 | $0.637 |
| Context window | 1.0M | 524K |
| Max output | 512K | 262K |
| Released | May 2026 | Jul 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 90.9% | 88.5% |
| OTIS Mock AIME | 71.1% | 90.0% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose MiniMax M3 if…
- Costs less per token — $0.525 vs $0.637 blended
- Higher GPQA Diamond (90.9% vs 88.5%)
- Larger context window (1.0M)
Choose Inkling Small if…
- Higher OTIS Mock AIME (90.0% vs 71.1%)
- Newer model (released Jul 2026)
FAQ
Which is better, MiniMax M3 or Inkling Small?
Across the 2 benchmarks both models have independently-run scores for, MiniMax M3 leads on 1 and Inkling Small leads on 1. Benchmarks are one input — price and context window are on this page too.
Is MiniMax M3 cheaper than Inkling Small?
MiniMax M3 is cheaper: $0.525 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.300 vs $0.450. Output alone: $1.20 vs $1.20.
What context windows do MiniMax M3 and Inkling Small have?
MiniMax M3: 1,048,576 tokens. Inkling Small: 524,288 tokens.
Who makes MiniMax M3 and Inkling Small?
MiniMax M3 is made by MiniMax. Inkling Small is made by Thinkingmachines.