DeepSeek Search benchmarked: cheapest per search, mid-pack on quality
- Source
- x.com
- Date
DeepSeek Search debuts on the Artificial Analysis Search Index at 69, 17th of 27 search products, at the lowest price of any paid Search API on the board @deepseek_ai launched its Search API on 17 October. We benchmarked it in our Stirrup agent harness, where GPT-5.6 Luna (medium) calls DeepSeek Search as its web_search tool to complete a combination of tasks from BrowseComp, DeepSearchQA and AA-Omniscience. At $0.75 per 1k searches, DeepSeek Search costs less per search than any other paid Search API we benchmark, below Octen, Parallel (turbo) and Parallel (fast) at $1. At about $0.032 per task, it is the 5th cheapest of 27 products, cheaper than 20 of the other 25 Search APIs (median $0.066) and level with Nimble (lite). TinyFish, Octen, Parallel (turbo) and Parallel (fast) cost less. Key benchmarking results for DeepSeek Search: ➤ Artificial Analysis Search Index: DeepSeek Search scores 69, a 36-point lift over the same model with no search (33). It sits between TinyFish at 71 and Linkup (standard) at 68 ➤ AA-Omniscience is DeepSeek Search's strongest benchmark: it scores 70% accuracy on our proprietary factual answer benchmark. This ranks 10th of 27, 3 points behind the…

If your agent calls a search API, DeepSeek Search costs $0.75 per 1k searches and scores 69 on the index, but returns large results that raise model cost, and it rejects queries over 128 characters.
- DeepSeek Search costs $0.75 per 1,000 successful searches, the lowest per-search price of any paid Search API Artificial Analysis benchmarks, and DeepSeek does not bill empty results.
- Paired with GPT-5.6 Luna, it scores 69 on the Artificial Analysis Search Index, a 36-point lift over the same model without search, but ranks 25th of 27 on BrowseComp, where answers need multi-hop reasoning across several searches.
- Each search returns about 7,000 , which raises model cost to about $0.023 per task, second highest on the board, though the total of about $0.032 per task still ranks 5th cheapest of 27.
- DeepSeek rejects queries over 128 characters. In testing, 6% of the 's searches hit that limit, and the model's first shorter rewrite succeeded for 87% of them.
Checking sign-in…
Loading comments…






