← Blog
ANNOUNCEMENT

A dollar for $40 of DeepSeek V4 Pro usage

Hard to say no to that. how did we make deepseek outperform opus 4.7? btw we've raised $5M from the best investors in silicon valley, we got you!!

Team Command Code
2 min read
May 20, 2026

Hard to say no to that.

CommandCode.ai/pricing

how did we make deepseek outperform opus 4.7?

btw we've raised $5M from the best investors in silicon valley, we got you!!

Command Code is the 3rd most coding agent / harness in weeks after going live. open > closed. you might wanna check out what devs are talking about in the thread quoted here

DeepSeek V4 Pro at a glance

Hybrid-attention long-context reasoning.

SpecDeepSeek V4 Pro
Model IDdeepseek/deepseek-v4-pro
Context window1M tokens
ReleasedAugust 13, 2026
Intelligence Index36
Coding Index68.8
Input$0.66 per 1M tokens
Output$1.98 per 1M tokens
Cache read$0.02 per 1M tokens
Effective input in an agent loop$0.21 per 1M tokens
PlansGo and above

Specs, pricing and plans are from the DeepSeek V4 Pro 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 Pro

1cmd --model deepseek/deepseek-v4-pro

Or type /model in a session and pick it. You can switch mid-session without losing context.

What real work costs on DeepSeek V4 Pro

TaskTokens (in · out)Cost
Quick lookup / one-liner8K · 1K$0.0027
Review a 500-line PR60K · 4K$0.02
Fix a bug (agent loop)180K · 12K$0.06
Refactor a module320K · 20K$0.10
Full-repo agent run900K · 45K$0.24

Try Command Code

The best coding agent for open models, in your terminal or on your desktop.

1npm i -g command-code

Desktop App · Docs · X · Discord

Share this article