DeepSeek Search/Fetch APIs bill per call at $0.75 per 1,000: what agent harnesses should change
A breakdown of DeepSeek's docs: only successful calls are billed, count up to 50 at no extra cost, fetch only results with rerank_score above 1.5, 5 QPS per account, plus vendor Terminal-Bench 4.0 numbers of 42.3 vs Opus 5's 51.8.
DeepSeek's new Search and Fetch APIs are priced per call, not per token. If you build agent harnesses, a few defaults should change this week. What's in DeepSeek's docs, and what I'd do about it: 1. $0.75 per 1,000 calls on each endpoint, billed only when a call returns a result. Empty searches, failures and timeouts cost nothing. So a miss is free, and you only pay for the retry that actually finds something. 2. count goes up to 50 and doesn't change the price. If your harness asks for 5 results and then searches again, ask for more the first time. 3. Every result comes with a rerank_score (0 to 3) and a 600 to 800 character summary meant to be read by a model. DeepSeek calls 1.5 and up high quality. I'd only fetch pages above that line. Each fetch is another billed call. 4. The rate limit is 5 QPS for Search and 5 for Fetch per account, whichever key you use. Eight parallel subagents share those 5. Handle 429s. 5. Calls through DeepSeek Harness, Claude Code or Codex are free until 00:00 Beijing on Nov 1. Use the window to log how many calls a typical task makes before anyone bills you for them. 6. It's the same key as the model API. One leaked key now pays for model, search and fetch. After the OpenCode Console breach, rotate any key you've pasted into a third-party tool. On the model itself: DeepSeek's own table has V4.1-Flash-1017 at 42.3 on Terminal-Bench 4.0, up from 31.2. Opus 5 sits at 51.8, and that's last generation's Opus. These are vendor numbers and haven't been independently reproduced.