Thinking Machines: Inkling 2 Mini vs NVIDIA: Nemotron 3.5 Super VL
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-21.
| Thinking Machines: Inkling 2 Mini | NVIDIA: Nemotron 3.5 Super VL | |
|---|---|---|
| Vendor | thinkingmachines | nvidia |
| Quality Score | 100 | 100 |
| Input Price | $0.10/M | $0.15/M |
| Output Price | $0.40/M | $0.47/M |
| Context Window | 1,048,576 | 1,048,576 |
| Max Output | 65,536 | 943,718 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Inkling 2 Mini costs $0.20 and Nemotron 3.5 Super VL costs $0.27, so Inkling 2 Mini is about 1.3 times cheaper for the same work.
Both read up to 1,048,576 tokens at once, roughly 1,573 pages of text.
Only Nemotron 3.5 Super VL offers video input.
Across the 1 tasks where they differ, Inkling 2 Mini scores higher on 1 (Blog Post Writing).
Inkling 2 Mini was released in November 2026 and Nemotron 3.5 Super VL in October 2026.
Pick Inkling 2 Mini if you need lower cost; pick Nemotron 3.5 Super VL if you need video 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 | Thinking Machines: Inkling 2 Mini | NVIDIA: Nemotron 3.5 Super VL |
|---|---|---|
| Blog Post Writing | 122 | 121 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →