Relace
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...
- Context window
- 256Ktokens
- Max output
- 128Ktokens
- Input
- $1.00/ 1M
- Output
- $3.00/ 1M
Quick start
from openai import OpenAI
client = OpenAI(
base_url="https://neurongate.net/v1",
api_key="sk-ng-your-api-key",
)
completion = client.chat.completions.create(
model="relace/relace-search",
messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)Cost
| Example request | Tokens | Cost |
|---|---|---|
| Short prompt | 1K in | $0.001 |
| Typical chat turn | 1K in · 500 out | $0.0025 |
| Document analysis | 10K in · 2K out | $0.016 |
| Long context | 100K in · 10K out | $0.13 |
Prices in USD. Billed per token actually used, from a balance prepaid in USDT, USDC, ETH or BTC.
Frequently asked questions
What is 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...
How much does Relace Relace Search cost?
Relace Relace Search is priced at $1 per 1 million input tokens and $3 per 1 million output tokens when accessed via NeuronGate. You pay per token — no subscriptions required. Top up with crypto (USDT, USDC, ETH, BTC).
Does Relace Relace Search support streaming?
Yes, Relace Relace Search supports streaming responses via NeuronGate's API. Use the standard "stream": true parameter in your request.
What is the context window of Relace Relace Search?
Relace Relace Search has a context window of 256K tokens (~192K words). Maximum output is 128K tokens.
Does Relace Relace Search support function calling (tools)?
Yes, Relace Relace Search supports function calling / tool use via NeuronGate's standard API.
How do I use Relace Relace Search with NeuronGate?
Create a NeuronGate account, top up your balance with crypto, generate an API key, and use the model id relace/relace-search in your requests. NeuronGate uses the OpenAI-compatible API format — set your base URL to https://neurongate.net/v1.