Relace: Relace Search
Relace Search is a text-in, text-out model from Relace with a 256,000-token context window and a 128,000-token output ceiling. It supports tool use, which makes it usable in agentic pipelines, but it does not support reasoning modes and has no documented structured output capability. There is no open-weights release, and input is limited to text only. At $1.00 per million input tokens and $3.00 per million output tokens, the pricing is competitive for a search-oriented tool-capable model, but there is currently no independent benchmark coverage to validate quality claims. Buyers who need long-context retrieval pipelines with tool integration may find it worth trialing, but anyone requiring third-party performance data before committing budget should note that this model is unproven on that front and carries real evaluation risk.
- Model ID
- relace/relace-search
- Vendor
- relace
- Released
- December 2025
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 128,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $1.00/M input and $3.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.03 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.65 |
| A month of a busy support chatbot | 5M in / 2M out | $11.00 |
Similar models
Quick answers
- How much does Relace: Relace Search cost?
- $1.00 per million input tokens and $3.00 per million output tokens.
- What is Relace: Relace Search's context window?
- 256,000 tokens, roughly 384 pages of text in a single request.
- Does Relace: Relace Search support tool calling?
- It supports tool calling, structured output.
- Can Relace: Relace Search process images?
- No, it is text-only on the input side.