Context
256K tokens (~128 books)
Input $/1M
$1.00
Output $/1M
$3.00
Type
text
License
Proprietary
Benchmarks
0 tested
Data updated today
About
The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...
No benchmark data available yet.
Links
Research
Documentation
Community
BenchGecko API
relace-search
Specifications
- Typetext
- Context256K tokens (~128 books)
- ReleasedDec 2025
- LicenseProprietary
- StatusActive
- Cost / Message~$0.005
Available On
Learn More
Share & Export
Frequently Asked Questions
Relace Search is a proprietary text AI model by relace, released in December 2025. Context window: 256K tokens.