Inkling by Thinking Machines Lab is now live in Command Code.
- Available on all plans (Go, Pro, Max, Team)
- Multimodal: text, image, audio
- Parameters: 975B total, 41B active
- $1.00/M input, $4.05/M output
How to use?
- $ cmd update or $ npm i -g command-code@latest
- Switch with /model
Inkling at a glance
Multimodal MoE reasoning.
| Spec | Inkling |
|---|---|
| Model ID | thinkingmachines/inkling |
| Context window | 256K tokens |
| Released | July 15, 2026 |
| Intelligence Index | 25 |
| Coding Index | 52.1 |
| Input | $1 per 1M tokens |
| Output | $4.05 per 1M tokens |
| Cache read | $0.17 per 1M tokens |
| Effective input in an agent loop | $0.42 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the Inkling model page as of September 28, 2026, including any deal running that day, so they can differ from the launch pricing above. Intelligence and Coding Index scores are from Artificial Analysis.
Use Inkling
1cmd --model thinkingmachines/inklingOr type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on Inkling
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0061 |
| Review a 500-line PR | 60K · 4K | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.12 |
| Refactor a module | 320K · 20K | $0.21 |
| Full-repo agent run | 900K · 45K | $0.50 |
Try Command Code
The best coding agent for open models, in your terminal or on your desktop.
1npm i -g command-codeDesktop App · Docs · X · Discord
