PrismML: Ternary Bonsai 2 27B vs Thinking Machines: Inkling Small
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| PrismML: Ternary Bonsai 2 27B | Thinking Machines: Inkling Small | |
|---|---|---|
| Vendor | prism-ml | thinkingmachines |
| Quality Score | 100 | 100 |
| Input Price | $0.07/M | $0.45/M |
| Output Price | $0.50/M | $1.20/M |
| Context Window | 262,144 | 524,288 |
| Max Output | 32,768 | 262,144 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | - |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | ✓ |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Ternary Bonsai 2 27B costs $0.20 and Inkling Small costs $0.75, so Ternary Bonsai 2 27B is about 3.8 times cheaper for the same work.
Inkling Small reads up to 524,288 tokens at once, roughly 786 pages of text, against about 393 pages for Ternary Bonsai 2 27B.
Only Ternary Bonsai 2 27B offers structured output; only Inkling Small offers audio input.
Across the 20 tasks where they differ, Ternary Bonsai 2 27B scores higher on 12 (SQL Generation, Unit Test Generation, Regex Writing and others), Inkling Small on 8 (Code Review, Code Completion, Code Refactoring and others).
Ternary Bonsai 2 27B was released in September 2026 and Inkling Small in July 2026.
Pick Ternary Bonsai 2 27B if you need lower cost or structured output; pick Inkling Small if you need long documents or audio input.
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 27B | Thinking Machines: Inkling Small |
|---|---|---|
| SQL Generation | 131 | 125 |
| Code Review | 126 | 128 |
| Code Completion | 129 | 131 |
| Code Refactoring | 127 | 132 |
| Bug Fixing | 130 | 136 |
| Unit Test Generation | 121 | 116 |
| Code Documentation | 126 | 131 |
| Regex Writing | 119 | 119 |
| CI/CD Pipelines | 117 | 116 |
| Frontend Component Design | 122 | 118 |
| Data Analysis | 124 | 120 |
| CSV / Spreadsheet Cleanup | 128 | 121 |
| ETL Scripting | 122 | 124 |
| JSON Extraction | 131 | 119 |
| Bulk Data Labeling | 129 | 125 |
| OCR / Document Parsing | 128 | 123 |
| Table Extraction from PDFs | 128 | 123 |
| Long-Document Summarization | 129 | 137 |
| Short-Form Summarization | 123 | 123 |
| Blog Post Writing | 119 | 121 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →