$ diff grok-4-7 ternary-bonsai-2-27b
Grok 4.7 vs Ternary Bonsai 2 27B
Values come from Grok 4.7 and Ternary Bonsai 2 27B, where each is cited to its source. This page states no benchmark result and ranks neither model — it puts two published specifications next to each other. Where a lab has not published a figure, the row says so rather than guessing.
xAIGrok 4.7
- context
- 500K
- weights
- —
- $/M in
- $2
- $/M out
- $6
- context
- 262K
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Grok 4.7 takes 500K against 262K — modestly more room in a single request.
- Recency
- Grok 4.7 shipped 4 days after Ternary Bonsai 2 27B (2026-09-21 vs 2026-09-17).
Full spec
| Attribute | Grok 4.7 | Ternary Bonsai 2 27B |
|---|---|---|
| Developer | xAI | Prismml |
| Released | 2026-09-21 | 2026-09-17 |
| Context window | 500K | 262,144 |
| Pricing | $2/M input · $0.50/M cached input · $6/M output (prompts ≤200K); $4/M · $1/M · $12/M above 200K | not recorded |
| License | not recorded | Apache 2.0 |
| Availability | Grok API, Cursor, Grok Build, OpenRouter, Vercel, Cloudflare | Hugging Face (`prism-ml/Ternary-Bonsai-2-27B-gguf`, `prism-ml/Ternary-Bonsai-2-27B-mlx-2bit`) |