Capabilities
7-day heat trend
−31.6%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 12% of tracked models
- Faster than 17% of tracked models
- Efficiency rank: #496 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About 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 is a Text model from Relace (US). HotON.ai tracks it at $1.00 per 1M input tokens and $3.00 per 1M output tokens, with a 256K-token context window, ~129 tokens/sec throughput and 97.3% availability. Its composite efficiency score is 89/100 at an estimated $0.004 per successful task.
Compare relace-search
Related market news
Frequently asked questions
How much does relace-search cost per 1M tokens?+
relace-search is tracked at $1.00 per 1M input tokens and $3.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $2.50 per 1M tokens. Figures are illustrative demo data.
What is relace-search best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is relace-search?+
relace-search delivers about 129 tokens/sec with 97.3% tracked availability, suitable for latency-sensitive, real-time applications.
Is relace-search cheaper than other AI models?+
Within the HotON.ai tracked set, relace-search is cheaper than 12% of models on input price and ranks #496 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.