PrismML: Ternary Bonsai 2 9B vs Cohere: Command A+
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-02.
| PrismML: Ternary Bonsai 2 9B | Cohere: Command A+ | |
|---|---|---|
| Vendor | prism-ml | cohere |
| Quality Score | 100 | 100 |
| Benchmark Score | - | 32.5 |
| Input Price | $0.08/M | $0.30/M |
| Output Price | $0.13/M | $1.50/M |
| Context Window | 262,144 | 192,000 |
| Max Output | 65,536 | 64,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | - | 37.1 |
| ai_index_agentic | - | 15.1 |
| ai_index_coding | - | 45.9 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Ternary Bonsai 2 9B costs $0.11 and Command A+ costs $0.68, so Ternary Bonsai 2 9B is about 6.0 times cheaper for the same work.
Both take in a similar amount of text: 262,144 and 192,000 tokens, about 393 and 288 pages.
Across the 20 tasks where they differ, Ternary Bonsai 2 9B scores higher on 1 (Code Completion), Command A+ on 19 (SQL Generation, Code Review, Code Refactoring and others).
Ternary Bonsai 2 9B was released in October 2026 and Command A+ in September 2026.
Pick Ternary Bonsai 2 9B if you need lower cost; pick Command A+ if you need the stronger all-round task scores.
Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.
Who wins by task?
| Task | PrismML: Ternary Bonsai 2 9B | Cohere: Command A+ |
|---|---|---|
| SQL Generation | 131 | 144 |
| Code Review | 126 | 137 |
| Code Completion | 129 | 128 |
| Code Refactoring | 127 | 134 |
| Bug Fixing | 130 | 143 |
| Unit Test Generation | 121 | 131 |
| Code Documentation | 126 | 128 |
| Regex Writing | 120 | 126 |
| CI/CD Pipelines | 117 | 125 |
| Frontend Component Design | 122 | 131 |
| Data Analysis | 124 | 140 |
| CSV / Spreadsheet Cleanup | 128 | 134 |
| ETL Scripting | 122 | 130 |
| JSON Extraction | 132 | 139 |
| Bulk Data Labeling | 129 | 131 |
| OCR / Document Parsing | 128 | 133 |
| Table Extraction from PDFs | 128 | 133 |
| Long-Document Summarization | 129 | 134 |
| Short-Form Summarization | 124 | 126 |
| Blog Post Writing | 119 | 124 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →