DeepSeek updated its official pricing page: starting 12:00 on November 18, 2026 (Beijing Time, UTC+8), server-side web search and web fetch triggered during a model call are no longer billed, and only model token usage is charged. This covers the web tools, the web_search tool in the Anthropic API and the web_search tool in the Responses API. Calling the standalone Search API or Fetch API directly is still billed at $0.75 per 1,000 successful requests. When DeepSeek opened its app capabilities to the API on November 13, it said these extended capabilities carried tool fees on top of token charges.
Key Takeaways
- ✓Effective from 12:00 on November 18, 2026, Beijing Time (04:00 UTC)
- ✓Now free: server-side web search and fetch triggered inside a model call, including the web tools and the web_search tool in the Anthropic API and the Responses API
- ✓Still billed: direct calls to the standalone Search API and Fetch API, at $0.75 per 1,000 successful requests
- ✓Model prices unchanged: deepseek-flash (DeepSeek-V4.1-Flash-1017) costs $0.3 per 1M cache-miss input tokens and $1.2 per 1M output tokens at peak, half price off-peak
- ✓For agent builders: letting the model search on its own is now cheaper than wiring a separate search API, but search results added to the context still count as input tokens
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
On November 13 DeepSeek opened its app features, such as web search, URL reading and file parsing, to the API, and said these extended capabilities carried tool fees on top of token charges. For teams building search-heavy agents, a separate charge for every search and fetch made costs hard to predict.
How it works
The official pricing page now states that from 12:00 on November 18 (Beijing Time), server-side search and web fetch triggered during a model call are no longer billed; only model tokens are charged. This applies to the web tools, the web_search tool in the Anthropic API and the web_search tool in the Responses API. Direct calls to the standalone Search API and Fetch API are still billed at $0.75 per 1,000 successful requests.
Benchmarks
This is a pricing change; DeepSeek published no new benchmarks. Model prices are unchanged: deepseek-flash costs $0.3 per 1M cache-miss input tokens and $1.2 per 1M output tokens at peak, with off-peak at half price.
What it means for developers
If your agent uses deepseek-flash with the web_search tool, the searches themselves no longer cost extra, so you may not need a separate search API. Search results added to the context still count as input tokens, and the standalone Search and Fetch APIs remain billed per request.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.