Relace Search
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...
Relace Search ranks #254 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $2.00 blended per million tokens, it is cheaper than 34% of models with published API pricing. Its 256,000-token context window is about the catalog median (262,144 tokens).
texttext->text
Context
Max context: 256000
Max output: 128000
Max output: 128000
Pricing
Input / 1M: 1.00
Output / 1M: 3.00
Blend / 1M: 2.00
Output / 1M: 3.00
Blend / 1M: 2.00
Quality
Quality index: —
Provider
Provider: Relace
Moderated: no
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $2.00per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $2.00 |
| 10,000,000 | $20.00 |
| 100,000,000 | $200.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Relace
- Relace Apply 3$1.05 / 1M
Closest API price
- Hermes 4 405B$2.00 / 1M
- Nova Pro 1.0$2.00 / 1M
- GLM 5.1$2.00 / 1M · Q 83.3
- GLM 5.2$2.00 / 1M
- Qwen3.5 397B A17B$2.02 / 1M · Q 66.0