Router DeskHomeRelace
Relace
Two coding models under one maker page: Search and Apply. They are not general chat aliases.
Updated 2026-09-27
OpenRouter’s Relace page says you can call Relace models through the same API, and names Relace Search and Relace Apply. On 27 Sep 2026 the page showed Search at $1 per million input tokens and $3 per million output tokens, and Apply at $0.85 and $1.25. Both cards showed a 256,000-token context. Search was dated 8 Dec 2025. Apply was dated 26 Sep 2025.
Use them when your agent is doing repo search or patch apply and you have evals on these ids. For a general coding model, compare them with DeepSeek V4 Flash and Qwen3.7 Max on the coding-models page. The base URL does not change.
Questions
What is Relace on OpenRouter?
A maker with a handful of coding models, including Relace Search and Relace Apply.
How much do they cost?
On 27 Sep 2026, Search was $1 / $3 per million tokens and Apply was $0.85 / $1.25, each with a 256K context.
Where is the page?
https://openrouter.ai/relace
Related
- Coding models
Coding-model choice on OpenRouter is price, context, and tool-call reliability. DeepSeek V4, Qwen3.7 Max, GLM 5.2, and Sonnet 5 are the slugs to price first.
- OpenCode and OpenRouter
OpenCode is an open-source coding agent. Connect OpenRouter with /connect in the terminal, or the same credentials in the desktop app.
- DeepSeek V4 Flash price
DeepSeek V4 Flash 0731 was $0.021 / $0.32 per million tokens on 27 Sep 2026. The 0423 slug was $0.047 / $0.094. Neither was the free router.
- OpenRouter API URL
The OpenRouter base URL is https://openrouter.ai/api/v1. Chat calls go to /chat/completions with a Bearer key.