Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.0000016 | $1.60 |
| completion | 0.0000048 | $4.80 |
| web_search | 0.005 | $5000 |
| input_cache_read | 0.0000004 | $0.400 |
| overrides | [object Object] | — |
{
"temperature": 0.7,
"top_p": 0.95
}