Claude Haiku 4.5 vs Ternary Bonsai 2 9B
Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Ternary Bonsai 2 9B (Prism Ml). Green cells mark the better value in each row.
Prices updated Nov 18, 2026, 12:28 AM UTC · refreshed nightly
| Claude Haiku 4.5 Anthropic | Ternary Bonsai 2 9B Prism Ml | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.00 | $0.08 |
| Output $/1M | $5.00 | $0.13 |
| Blended $/1M (3:1) | $2.00 | $0.092 |
| RAG example (30K in / 2K out) | $0.04 | $0.00266 |
| Quality & speed | ||
| Intelligence Index | 7.4 | — |
| Coding Index | 43.9 | — |
| Agentic Index | 8 | — |
| Output speed (tok/s) | — | — |
| Time to first token | — | — |
| Specs | ||
| Context window | 200K | 262K |
| Input modalities | text, image, file | text, image |
FAQ
Which is cheaper, Claude Haiku 4.5 or Ternary Bonsai 2 9B?
Ternary Bonsai 2 9B has the lower blended API price at $0.092 per 1M tokens (3:1 input:output mix), versus $2.00 for the other model. Prices are live from OpenRouter and refresh nightly.
Which is better for RAG workloads?
For a typical RAG request (30K input / 2K output tokens), Ternary Bonsai 2 9B costs about $0.00266 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Ternary Bonsai 2 9B offers 262K.
Which scores higher on Artificial Analysis benchmarks?
Claude Haiku 4.5 leads on the Artificial Analysis Intelligence Index (7.4 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.