DeepSeek V4 Flash Fast is now available in Command Code. 2x usage in GOAT. Available all plans and API 🐐
DeepSeek V4 Flash Fast has 300-500 TPS. Enjoy working super fast as you need it.
Pricing:
- INPUT: $0.28
- OUTPUT: $0.56
- CACHE: $0.07
Plans:
- GOAT plan has 2x usage. $10/mo has $20 usage limit.
- Available in GOAT and above plans.
DeepSeek V4 Flash Fast at a glance
Low-latency V4 Flash deployment.
| Spec | DeepSeek V4 Flash Fast |
|---|---|
| Model ID | deepseek/deepseek-v4-flash-fast |
| Context window | 1M tokens |
| Released | August 22, 2026 |
| Input | $0.28 per 1M tokens |
| Output | $0.56 per 1M tokens |
| Cache read | $0.07 per 1M tokens |
| Effective input in an agent loop | $0.13 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the DeepSeek V4 Flash Fast 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 Fast
1cmd --model deepseek/deepseek-v4-flash-fastOr type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on DeepSeek V4 Flash Fast
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0013 |
| Review a 500-line PR | 60K · 4K | $0.01 |
| Fix a bug (agent loop) | 180K · 12K | $0.03 |
| Refactor a module | 320K · 20K | $0.05 |
| Full-repo agent run | 900K · 45K | $0.13 |
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
