# DeepSeek opens Search and Fetch APIs at $0.75 per 1,000 calls, with a temporary agent-tool free window

DeepSeek's October 17 release opens its Search and Fetch endpoints beyond internal use, pricing each at $0.75 per 1,000 calls. Supported server-side agent-tool use is temporarily free for DeepSeek API customers until October 31, but production search quality and billing details need independent verification.

Developers get another paid web retrieval option for coding agents and applications; the introductory harness exemption expires October 31.

- Status: Active
- Published: 2026-10-18T22:03:52+13:00
- Updated: 2026-10-18T22:03:52+13:00
- Categories: Artificial Intelligence, Web Development, AI Agents, Inference & APIs, Developer Tools
- Tags: AI agents, API pricing, DeepSeek
- Canonical HTML: https://beyondthe.news/dossiers/deepseek-search-fetch-api-pricing-agent-tools-october-2026

## What changed

On October 17, 2026 DeepSeek announced that its Search and Fetch APIs are open to all developers. It lists $0.75 per 1,000 calls for each endpoint. Server-side calls made through DeepSeek Harness, Claude Code and Codex are currently free for DeepSeek API users, with billing beginning October 31, 2026 at 16:00 UTC. The announcement coincides with DeepSeek-V4.1-Flash-1017, a new open-weight model revision with claimed coding-agent improvements; that model is related context, not a prerequisite for every search API use. DeepSeek says the underlying search engine serves hundreds of millions of requests daily, but that capacity claim and independent retrieval quality have not been verified.

## Why it matters

Web retrieval is a recurring variable cost for coding agents, research workflows and answer systems. A published per-call rate makes DeepSeek a potential alternative to building a search index or relying on a single provider. At the announced list rate, 10,000 Search calls would cost $7.50 before any other model, Fetch, infrastructure or tool charges; 10,000 Search plus 10,000 Fetch calls would cost $15. Developers using the temporary server-side exemption should budget for its expiry and test the actual API's relevance, freshness, content extraction, latency, geographic access, rate limits and acceptable-use conditions before committing production workloads. A provider announcement is not an independent quality benchmark.

## Search and Fetch are separate metered endpoints

DeepSeek's October 17 announcement prices each endpoint at $0.75 per 1,000 calls. A workflow that searches and then fetches a page may incur both types of call. The public announcement does not establish a bundled allowance or guarantee that every result can be fetched. Model token charges, if applicable, are separate from these per-call rates.

## A free period applies to specific agent-tool paths

DeepSeek says Search and Fetch calls via server-side tools in DeepSeek Harness, Claude Code and Codex are temporarily free for DeepSeek API users. Billing is scheduled to begin at 16:00 UTC on October 31, 2026. This is not described as unlimited free public API access or a permanent waiver; developers should confirm account-specific eligibility and billing before relying on it.

## The model update is a separate release

DeepSeek-V4.1-Flash-1017 is available in the DeepSeek app and API, with downloadable weights linked from the release note. DeepSeek claims shorter answers and faster task completion than the prior V4.1 Flash model, using its own benchmark setup. Those claims should not be treated as independently reproduced performance. BTN already covers the underlying V4.1 Flash model line in dossier #84.

## What to test before switching retrieval providers

Compare query coverage, freshness, citations, page extraction fidelity, failure and retry behaviour, latency and total cost on representative workloads. Separate Search and Fetch counts in telemetry. Revisit costs after the October 31 exemption ends, and check whether the provider's API and billing documentation specify additional limits.

## Key details

- Announced October 17, 2026 in DeepSeek's official release note.
- Search API: $0.75 per 1,000 calls.
- Fetch API: $0.75 per 1,000 calls.
- Server-side tools in DeepSeek Harness, Claude Code and Codex temporarily exempt for DeepSeek API users.
- Free agent-tool exemption scheduled to end October 31, 2026 at 16:00 UTC.
- 10,000 calls to either endpoint cost $7.50 at announced list price, excluding any other charges.
- DeepSeek-V4.1-Flash-1017 model revision launched alongside the retrieval APIs.
- No independent retrieval quality or uptime benchmark was established.

## Builder takeaways

- Instrument Search and Fetch usage separately to avoid hidden tool-cost surprises.
- Test search relevance and fetch extraction on your own queries and domains before switching.
- Budget for the October 31 end of the server-side agent-tool waiver.
- Keep model token billing separate from retrieval calls when estimating unit economics.
- Treat DeepSeek's performance and scale figures as vendor claims until independently tested.

## What to watch

- Published Search and Fetch API reference documentation and rate limits.
- Clarification of regional availability, data retention and acceptable-use policies.
- Actual billing behaviour after October 31 at 16:00 UTC.
- Independent search quality, latency and extraction benchmarks.
- Model-compatibility or endpoint changes tied to V4.1 Flash revisions.

## Uncertainties

- No independent comparative retrieval benchmark available at the time of research.
- The announcement does not fully specify account-level quotas or contractual limits.
- The precise eligibility for temporary free server-side tool calls may depend on account and integration.
- Search engine traffic volume is a DeepSeek claim, not independently verified.

## Sources

- [DeepSeek-V4.1-Flash-1017: Wish-Driven Programming Made Real](https://api-docs.deepseek.com/news/news261017/) — DeepSeek API Docs · primary announcement · 2026-10-17T00:00:00+13:00. Official public Search and Fetch availability, per-call pricing, server-side tool exemption and October 31 billing deadline; vendor model claims.
- [AI model releases 2026 tracker](https://siliconainews.com/tracker/ai-model-releases) — Silicon AI News · independent release tracking · 2026-10-18T00:00:00+13:00. Independently tracks the October 17 DeepSeek model snapshot; does not verify retrieval API performance.

