TokenRoute
Get started
Back to models

Relace: Relace Search

relace/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...

Pricing

Input$0.7000 /M
Output$2.10 /M

Specs

Context length256K tokens
Max output128K tokens
Inputtext
Outputtext

Quickstart

Point the OpenAI SDK at https://tokenroute.app/api/v1 and use a TokenRoute API key.

bash
curl https://tokenroute.app/api/v1/chat/completions \
  -H "Authorization: Bearer $TOKENROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "relace/relace-search",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Supported parameters

max_tokens
response_format
seed
stop
temperature
tool_choice
tools
top_p