token.app › Compare › Inkling Small vs Grok 4.6
Inkling Small vs Grok 4.6
Grok 4.6 leads on 4 of 4 shared benchmarks. Inkling Small is 4.7× 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
| Inkling Small | Grok 4.6 | |
|---|---|---|
| Provider | Thinkingmachines | SpaceXAI |
| Input $/1M | $0.450 | $2.00 |
| Output $/1M | $1.20 | $6.00 |
| Blended $/1M | $0.637 | $3.00 |
| Context window | 524K | 500K |
| Max output | 262K | 450K |
| Released | Jul 2026 | Aug 2026 |
| Licence | Open weights | Proprietary |
| GPQA Diamond | 88.5% | 94.0% |
| FrontierMath T1–3 | 46.3% | 66.0% |
| FrontierMath T4 | 17.1% | 31.7% |
| OTIS Mock AIME | 90.0% | 99.2% |
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 Inkling Small if…
- Costs less per token — $0.637 vs $3.00 blended
- Larger context window (524K)
- Open weights — self-hostable
Choose Grok 4.6 if…
- Higher GPQA Diamond (94.0% vs 88.5%)
- Higher FrontierMath T1–3 (66.0% vs 46.3%)
- Higher FrontierMath T4 (31.7% vs 17.1%)
- Higher OTIS Mock AIME (99.2% vs 90.0%)
- Newer model (released Aug 2026)
FAQ
Which is better, Inkling Small or Grok 4.6?
Across the 4 benchmarks both models have independently-run scores for, Inkling Small leads on 0 and Grok 4.6 leads on 4. Benchmarks are one input — price and context window are on this page too.
Is Inkling Small cheaper than Grok 4.6?
Inkling Small is cheaper: $0.637 versus $3.00 per million tokens blended at 3:1 input:output. Input alone: $0.450 vs $2.00. Output alone: $1.20 vs $6.00.
What context windows do Inkling Small and Grok 4.6 have?
Inkling Small: 524,288 tokens. Grok 4.6: 500,000 tokens.
Who makes Inkling Small and Grok 4.6?
Inkling Small is made by Thinkingmachines. Grok 4.6 is made by SpaceXAI.