Relace Search
RelaceReleased Dec 8, 2025
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...
- Context window
- 256K tokens
- Max output
- 128K tokens
- Input
- text
- Output
- text
- Tokenizer
- Other
- Released
- Dec 8, 2025
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $1.00 | $0.030 | $1.03 |
| Output | $3.00 | $0.090 | $3.09 |
Supported parameters
- max_tokens
- response_format
- seed
- stop
- temperature
- tool_choice
- tools
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model relace/relace-search.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "relace/relace-search",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="relace/relace-search",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "relace/relace-search",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Relace Search cost via API?
- Through OpenKey, Relace Search costs $1.03 per 1M input tokens and $3.09 per 1M output tokens. That is the provider price ($1.00 / $3.00) plus a flat 3% fee — nothing else.
- What is Relace Search's context window?
- Relace Search accepts up to 256K tokens of context and returns up to 128K tokens per request.
- Is Relace Search OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "relace/relace-search" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Relace Search support?
- Relace Search accepts text input and produces text output.