$ diff claude-opus-5-5 ternary-bonsai-2-27b
Claude Opus 5.5 vs Ternary Bonsai 2 27B
Values come from Claude Opus 5.5 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.
AnthropicClaude Opus 5.5
- context
- 1M
- weights
- closed
- $/M in
- $4
- $/M out
- $20
- context
- 262K
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Claude Opus 5.5 takes 1M against 262K — 3.8× more room in a single request.
- Weights
- Ternary Bonsai 2 27B publishes weights (Apache 2.0); Claude Opus 5.5 is API-only. That decides self-hosting, air-gapped deployment and fine-tuning before any capability question does.
- Recency
- Claude Opus 5.5 shipped 5 days after Ternary Bonsai 2 27B (2026-09-22 vs 2026-09-17).
Full spec
| Attribute | Claude Opus 5.5 | Ternary Bonsai 2 27B |
|---|---|---|
| Developer | Anthropic | Prismml |
| Released | 2026-09-22 | 2026-09-17 |
| Context window | 1M tokens | 262,144 |
| Pricing | $4/M input · $20/M output · cache reads $0.20/M · cache writes $5/M | not recorded |
| License | proprietary (API-only; no weight release) | Apache 2.0 |
| Availability | Claude apps, Claude Code, Claude API as `claude-opus-5-5`, Amazon Bedrock, Google Cloud Vertex AI, Microsoft Foundry | Hugging Face (`prism-ml/Ternary-Bonsai-2-27B-gguf`, `prism-ml/Ternary-Bonsai-2-27B-mlx-2bit`) |