Relace: Relace Search✓ Catalog verified
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 multi-step reasoning to produce highly precise results 4x faster than any frontier model. It's designed to serve as a subagent that passes its findings to an "oracle" coding agent, who orchestrates/performs the rest of the coding task. To use relace-search you need to build an appropriate agent harness, and parse the response for relevant information to hand off to the oracle. Read more about it in the Relace documentation.
Overview
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 multi-step reasoning to produce highly precise results 4x faster than any frontier model. It's designed to serve as a subagent that passes its findings to an "oracle" coding agent, who orchestrates/performs the rest of the coding task. To use relace-search you need to build an appropriate agent harness, and parse the response for relevant information to hand off to the oracle. Read more about it in the Relace documentation.
Access: available through the official Relace API. Context window: 256K.
Specifications
| API identifier | relace/relace-search |
| Provider | Relace |
| Model type | Text LLM |
| Context window | 256K catalog |
| Input modalities | text |
| Output modalities | text |
| Released | Dec 8, 2025 |
| Moderated | No |
| Architecture modality | text->text |
API defaults
{
"top_p": null,
"temperature": null,
"frequency_penalty": null
}Pricing
Live pricing components for relace/relace-search as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $0.000001 | $1.00 / 1M | Per input token |
| Completion tokens | $0.000003 | $3.00 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$1.1Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | Not advertised | Image and document analysis support |
| Audio Processing | Not advertised | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | Not advertised | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call Relace: Relace Search through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="relace/relace-search",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| AI21: Jamba Large 1.7 | AI21 | 256K | $2.00 | View → |
| Cohere: Command A | Cohere | 256K | $2.50 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does Relace: Relace Search cost?
$1.00 per 1M input tokens and $3.00 per 1M output tokens on the official Relace API.
What is the context window of Relace: Relace Search?
Relace: Relace Search supports up to 256K tokens of context.
Does Relace: Relace Search support tool / function calling?
Yes, Relace: Relace Search supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access Relace: Relace Search?
Use the official Relace API with the model id `relace/relace-search`. See the Quick start section above for code examples.