GPT 6.1 Sol is now live in Command Code. It brings Astra-level intelligence at one-fifth of the price, with a 95% cache read discount. It's available on the Max plan and through the API.
GPT-6.1 Sol at a glance
Near-Astra performance for complex work at a lower cost.
| Spec | GPT-6.1 Sol |
|---|---|
| Model ID | openai/gpt-6.1-sol |
| Context window | 1.05M tokens |
| Released | September 29, 2026 |
| Intelligence Index | 51.8 |
| Input | $2 per 1M tokens |
| Output | $10 per 1M tokens |
| Cache read | $0.10 per 1M tokens |
| Effective input in an agent loop | $0.67 per 1M tokens |
| Plans | Max and above |
Specs, pricing and plans are from the GPT-6.1 Sol model page as of October 6, 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 GPT-6.1 Sol
1cmd --model openai/gpt-6.1-solOr type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on GPT-6.1 Sol
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.01 |
| Review a 500-line PR | 60K · 4K | $0.08 |
| Fix a bug (agent loop) | 180K · 12K | $0.22 |
| Refactor a module | 320K · 20K | $0.40 |
| Full-repo agent run | 900K · 45K | $0.92 |
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
