Relace Search
Provider：Relace
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...
Key specs
- Context：256K
- Max output：128K
- Tokenizer：Other
- Released：2025-12-08
Token pricing
- Input price：$1.00 / 1M tokens
- Output price：$3.00 / 1M tokens
- Blended price：$1.50 / 1M tokens
Modalities
Text
Use Cases
- Deep Reasoning & Analysis：Process long legal docs, academic papers, financial reports; multi-hop reasoning and evidence-chain tracing across huge contexts.（≈ $0.024/call）
- Chat & Support：FAQ auto-response, multi-turn dialogue, emotion detection — e-commerce, finance, gov.（≈ $0.0060/call）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
FAQ
- What is the token pricing of Relace Search? Input price $1.00 / 1M tokens, output price $3.00 / 1M tokens, blended about $1.50 / 1M tokens. Refer to Relace’s official page for the exact rate.
- What context window does Relace Search support? Context window is 256K, max output about 128K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Relace Search best for? Based on its capability and pricing, Relace Search fits best: Deep Reasoning & Analysis, Chat & Support. See the Use Cases section for details and cost estimates.
- What input/output modalities does Relace Search support? Supports Text modality.
- Is Relace Search a free model? Relace Search is billed per token, not a free model.
- Which provider offers Relace Search? Relace Search is offered by Relace.
More models from Relace
Full info：Relace Search