New in v0.26.11
Command Code supports Gemini 3.5 Flash. Pro-level coding, parallel agentic execution, 1M token context. Live in /model, same hour Google shipped it.
Gemini 3.5 Flash at a glance
Pro-level coding proficiency, parallel agentic execution.
| Spec | Gemini 3.5 Flash |
|---|---|
| Model ID | google/gemini-3.5-flash |
| Context window | 1M tokens |
| Released | May 19, 2026 |
| Intelligence Index | 32.6 |
| Coding Index | 70.1 |
| Input | $1.50 per 1M tokens |
| Output | $9 per 1M tokens |
| Cache read | $0.15 per 1M tokens |
| Effective input in an agent loop | $0.56 per 1M tokens |
| Plans | Pro and above |
Specs, pricing and plans are from the Gemini 3.5 Flash 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 Gemini 3.5 Flash
1cmd --model google/gemini-3.5-flashOr type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on Gemini 3.5 Flash
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.01 |
| Review a 500-line PR | 60K · 4K | $0.07 |
| Fix a bug (agent loop) | 180K · 12K | $0.20 |
| Refactor a module | 320K · 20K | $0.35 |
| Full-repo agent run | 900K · 45K | $0.81 |
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
