Relace: Relace Search
by RelaceRelace: Relace Search is a large language model from Relace. It costs $1.00 per million input tokens and $3.00 per million output tokens. Its context window is 256K tokens.
Tool callingStructured output
- Input / 1M tokens
- $1.00
- Output / 1M tokens
- $3.00
- Cached input / 1M
- -
- Context window
- 256K
Not supported
tokens
Who serves it cheapest
1 hosts serve Relace Search. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| RelaceCheapestbf16 | $1.00 | $3.00 | 256K | - | 100.0% |
About 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
| Model ID | relace/relace-search |
|---|---|
| Provider | Relace |
| Context window | 256K tokens |
| Max output | 128K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | No |
| Released | December 8, 2025 |
Cheaper alternatives
Models that cost less than Relace Search while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Relace: Relace Search cost?
$1.00 per million input tokens and $3.00 per million output tokens.
What is the context window of Relace: Relace Search?
256K tokens, with up to 128K tokens of output per request.