Capabilities
7-day heat trend
+3.9%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 43% of tracked models
- Faster than 80% of tracked models
- Efficiency rank: #956 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About repos-retrieve
Relace Repos Retrieve performs two-stage codebase retrieval using semantic search over Relace repositories.
repos-retrieve is a Text model from Relace (US). HotON.ai tracks it at $0.00 per 1M input tokens and $0.00 per 1M output tokens, with a 1K-token context window, ~164 tokens/sec throughput and 99.7% availability. Its composite efficiency score is 88/100 at an estimated $0.000 per successful task.
Compare repos-retrieve
Related market news
Frequently asked questions
How much does repos-retrieve cost per 1M tokens?+
repos-retrieve is tracked at $0.00 per 1M input tokens and $0.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.00 per 1M tokens. Figures are illustrative demo data.
What is repos-retrieve best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is repos-retrieve?+
repos-retrieve delivers about 164 tokens/sec with 99.7% tracked availability, suitable for latency-sensitive, real-time applications.
Is repos-retrieve cheaper than other AI models?+
Within the HotON.ai tracked set, repos-retrieve is cheaper than 43% of models on input price and ranks #956 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.