DeepSeek V4 Flash Vision Exp is now live in Command Code. GOAT/$10 per month · ~43K requests · ~2.2B tokens. Available across all plans and API. 🐐
DeepSeek V4 Flash Vision (exp) at a glance
Fast hybrid-attention reasoning with vision.
| Spec | DeepSeek V4 Flash Vision (exp) |
|---|---|
| Model ID | deepseek/deepseek-v4-flash-vision-exp |
| Context window | 1M tokens |
| Released | August 21, 2026 |
| Intelligence Index | 34.8 |
| Coding Index | 65 |
| Input | $0.15 per 1M tokens |
| Output | $0.60 per 1M tokens |
| Cache read | $0.003 per 1M tokens |
| Effective input in an agent loop | $0.05 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the DeepSeek V4 Flash Vision (exp) 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 DeepSeek V4 Flash Vision (exp)
1cmd --model deepseek/deepseek-v4-flash-vision-expOr type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on DeepSeek V4 Flash Vision (exp)
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0007 |
| Review a 500-line PR | 60K · 4K | $0.0052 |
| Fix a bug (agent loop) | 180K · 12K | $0.01 |
| Refactor a module | 320K · 20K | $0.03 |
| Full-repo agent run | 900K · 45K | $0.06 |
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
