Grok Code
No written verdict yet. Here is what commenters said.
6recommend
0warn against
Nov 2, 2025first mention
May 11, 2026latest mention
Why people recommend it
“I used it exclusively when it was free in Cursor and have nothing bad to say about it.”
“Grok code was my daily driver for months while it was free and it was fantastic”
Show 3 more
“I get more work done these days with GLM or Grok Code (using opencode)”
“lots of people are using it - presumably because it performs well and provides value.”
“I realized that it makes a huge difference.”
Caveats and dissent
No one in these comments warned against it.
Often compared with
Threads where it came up
- Grok 4 Fast now has 2M context window 3 mentions
- GitHub Copilot is deprecating Grok Code Fast 1 1 mention
- SpaceX and Cursor partnership. Right to acquire Cursor later this year 1 mention
- Muse Spark: Scaling Towards Personal Superintelligence 1 mention
- Anthropic bans use of API in OpenCode CLI tool 1 mention
- State of AI: An Empirical 100T Token Study with OpenRouter 1 mention
Also written as Grok Code, Grok Code Fast. Data: grok-code.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 10
“they're deprecating it because xAI is doing so upstream”
“I used it exclusively when it was free in Cursor and have nothing bad to say about it.”
“Grok code was my daily driver for months while it was free and it was fantastic”
“I get more work done these days with GLM or Grok Code (using opencode)”
“lots of people are using it - presumably because it performs well and provides value.”
“Will check out Grok Code Fast - thanks for the pointer.”
“I realized that it makes a huge difference.”
Yet if you go to the actual model’s page: https://openrouter.ai/x-ai/grok-code-fast-1 Cline and Kilo code are in the top 3. So how does that work? It’s considerably cheaper than competing models like 2.5 flash, though. So its not that surprising
“Grok Code Fast 1 is the most used model by a significant margin”
“I've found it to be many times faster and cheaper than Claude 4.5 or GPT 5 Codex while still being quite capable.”