DeepSeek V4.1 Flash Fast is now live in Command Code, with $60 of usage credits on the GOAT plan. 🐐 It runs at 250 to 300 tokens per second, has a 1M token context window, and serves the full-weight model as always. That means billions of tokens at two to three times the speed.
DeepSeek V4.1 Flash Fast at a glance
High throughput V4.1 Flash.
| Spec | DeepSeek V4.1 Flash Fast |
|---|---|
| Model ID | deepseek/deepseek-v4.1-flash-fast |
| Context window | 1M tokens |
| Released | September 28, 2026 |
| Input | $0.16 per 1M tokens |
| Output | $0.58 per 1M tokens |
| Cache read | $0.02 per 1M tokens |
| Effective input in an agent loop | $0.06 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the DeepSeek V4.1 Flash Fast model page as of October 6, 2026, including any deal running that day, so they can differ from the launch pricing above.
Use DeepSeek V4.1 Flash Fast
1cmd --model deepseek/deepseek-v4.1-flash-fastOr type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on DeepSeek V4.1 Flash Fast
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0008 |
| Review a 500-line PR | 60K · 4K | $0.0059 |
| Fix a bug (agent loop) | 180K · 12K | $0.02 |
| Refactor a module | 320K · 20K | $0.03 |
| Full-repo agent run | 900K · 45K | $0.07 |
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
