- Input price
- $1.00 / 1M tokens
- Output price
- $3.00 / 1M tokens
- Context window
- 256K tokens
- Longest reply
- 128K tokens
About this model
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...
Description from the model’s public catalogue listing.
Capabilities
- Reads
- Text
- Writes
- Text
- Reasoning mode
- No
- Tool calling
- Yes
- Open weights
- No
- Cached input
- Not listed
What it would cost
At list price, without caching or batch discounts.
- 1,000 chat replies2K tokens in, 500 out each
- $3.50
- Summarise 100 long reports50K tokens in, 1K out each
- $5.30
- A coding agent’s working day20M tokens in, 1M out
- $23.00
Price history
No change since we started tracking prices on 30 Sept 2026.
Alternatives at a similar price
From other labs, priced within about 40% of Relace Search, with a comparable context window.
- Qwen4 MaxQwen, 1M context$1.43 in$4.28 out
- ERNIE-Light-DT-1.0Baidu, 1.02M context$1.13 in$3.94 out
- GPT-6.1 Terra ProOpenAI, 1.05M context$1.00 in$5.00 out
- GPT-6.1 TerraOpenAI, 1.05M context$1.00 in$5.00 out
- Kimi K3.1 ProMoonshot, 1.05M context$0.24 in$8.40 out
- GlimpseElorian, 262K context$0.60 in$3.00 out