Relace Search
Relace
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...
What is Relace Search?
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...
Specifications
- Developer: Relace
- Context window: 256K tokens
- Max output: 128K tokens
- Input modalities: text
- Output modalities: text
- Input price: $1.00 per 1M tokens
- Output price: $3.00 per 1M tokens
- Knowledge cutoff: —
- Supported parameters: max_tokens, seed, stop, temperature, tool_choice, tools, top_p
Use Relace Search with PromptLayer
PromptLayer lets teams manage, evaluate, and observe prompts that run on Relace Search alongside every other model in their stack. Version prompts, run evals across models, and ship safe rollouts from the same dashboard.
Ready to try it yourself? Sign up for PromptLayer and start managing your prompts in minutes.