token.app › Compare › o4 Mini vs Inkling Small
o4 Mini vs Inkling Small
Inkling Small leads on 4 of 4 shared benchmarks. Inkling Small is 3.0× cheaper per token on a blended 3:1 basis. Inkling Small accepts the larger context window (524K).
Head to head
Blended price uses a 3:1 input:output mix
| o4 Mini | Inkling Small | |
|---|---|---|
| Provider | OpenAI | Thinkingmachines |
| Input $/1M | $1.10 | $0.450 |
| Output $/1M | $4.40 | $1.20 |
| Blended $/1M | $1.93 | $0.637 |
| Context window | 200K | 524K |
| Max output | 100K | 262K |
| Released | Apr 2025 | Jul 2026 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 79.6% | 88.5% |
| FrontierMath T1–3 | 36.1% | 46.3% |
| FrontierMath T4 | 4.9% | 17.1% |
| OTIS Mock AIME | 81.7% | 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 o4 Mini if…
- No clear advantage on the data we hold.
Choose Inkling Small if…
- Costs less per token — $0.637 vs $1.93 blended
- Higher GPQA Diamond (88.5% vs 79.6%)
- Higher FrontierMath T1–3 (46.3% vs 36.1%)
- Higher FrontierMath T4 (17.1% vs 4.9%)
- Higher OTIS Mock AIME (90.0% vs 81.7%)
- Larger context window (524K)
- Open weights — self-hostable
- Newer model (released Jul 2026)
FAQ
Which is better, o4 Mini or Inkling Small?
Across the 4 benchmarks both models have independently-run scores for, o4 Mini leads on 0 and Inkling Small leads on 4. Benchmarks are one input — price and context window are on this page too.
Is o4 Mini cheaper than Inkling Small?
Inkling Small is cheaper: $0.637 versus $1.93 per million tokens blended at 3:1 input:output. Input alone: $1.10 vs $0.450. Output alone: $4.40 vs $1.20.
What context windows do o4 Mini and Inkling Small have?
o4 Mini: 200,000 tokens. Inkling Small: 524,288 tokens.
Who makes o4 Mini and Inkling Small?
o4 Mini is made by OpenAI. Inkling Small is made by Thinkingmachines.