DeepSeek Search API pricing: $0.75 per 1,000 calls (Search) and related Fetch API pricing and caps; compare to Tavily, Brave, Exa, SerpAPI, Google/Bing grounding tools; article documents DeepSeek launch and its price, caps, and related details.
DeepSeek launched a Search & Fetch API priced at $0.75 per 1,000 successful requests with a rate limit of 5 requests per second, plus related generation cost and free testing window until Nov 1, 2026; this represents a material pricing and API endpoint change for web search and page fetching.
DeepSeek: Search & Fetch APIs priced at $0.75 per 1,000 successful requests; open to all developers; October 31, 2026 non-free for server-side tool calls from Claude Code, Codex, and DeepSeek Harness.
DeepSeek monetizes the agent retrieval layer at $0.75 per 1,000 calls (Search and Fetch endpoints), with per-request billing starting November 1 and 5 requests/sec per account cap; competitors’ pricing cited (Brave $5/1,000; Exa $7/$12; Tavily $5–$8; Perplexity Sonar $5+).
documents a material change: Parallel Search pricing and throughput details introduced (Turbo/Fast at $1 per 1,000 requests; Basic/Advanced at $5; 10 results included; 1 credit per basic search) along with references to DeepSeek’s pricing and throughput (5 req/sec per account) and that Parallel offers…
Perplexity Photon Search Engine and Fast Search mode launched; Fast Search costs $1.00 per 1,000 requests versus $5.00 for standard search, with comparable benchmarks and latency improvements; Photon introduces Rust-based search engine and pre-assembly ranking before LM response.
Web search in Vani now runs on Parallel · Vani AI.
Vertex AI release notes | Google Cloud Documentation.
DeepSeek Opens V4.1-Flash-1017 Weights and $0.75 Search API | AI Weekly.
DeepSeek launches web search and scraping API, API briefly appears as V4.1 Flash-1017 snapshot, Harness v0.2.1-rc1 released — 哲见 · WISE AI.
DeepSeek's Search & Fetch API price for both /v1/tools/search and /v1/tools/fetch is $0.75 per 1,000 successful requests; pricing indicated for the new DeepSeek-V4.1-Flash-1017 release and free trial window starts billing at 00:00 Beijing time on November 1, 2026.
Older models removed from the model docs; GPT-6 Astra and DeepSeek V4 Pro added — forck.
DeepSeek launches standalone Web Search and Fetch APIs for agents with priced per-1,000-successful-requests at $0.75; includes documentation and pricing details (Search: 1–50 results, default 10; Fetch: single URL up to 8,192 chars; 403/404 handling; limits: 5 qps for Search, 5 for Fetch; per-domain limit for Fetch).…
Tavily vs Exa vs Brave: The Page Text Costs More Than the Search | THE D*AI*LY BRIEF.
6 DeepResearch API Compared: OpenAI, Perplexity, Parallel, Tavily, Gemini, Valyu Features and Pricing — KBlip (source page)
documents a material change: a pricing/differentiation analysis of live web search vs enterprise RAG, including pricing details and recommendations, but it is a media analysis piece rather than an official product changelog from a provider.
Daily Neural Digest: LLM API price changes — what moved in the catalogue (2026-10-15 snapshot) tracking price and context-window changes in 455 OpenRouter/OpenAI-style models; new/removed models; context window adjustments; threshold rules documented on the page.
Perplexity API Pricing Tested: The Fee Is the Bill – Agent API pricing introduced by Perplexity, with key changes including replacement of Sonar API by Agent API, lower per-search fees ($2.50 per 1,000 vs $5), higher output token costs ($2.50 per 1M vs $1), and availability notes as of 14 October 2026.
You.com is now a connector in Merge Agent Handler with nine tools exposed via the Agent Handler MCP server, including live web search, content extraction, citations, multi-step research, finance research, image search, and account balance under a named connector; this represents a material product capability change…
The Inference article documents a material published change to Exa’s data indexing and pricing model: on October 6, Exa Places put 211 million business records on every API endpoint at no extra charge (free), following a $247,488,419 equity sale and prior May pricing changes. URL:
documents updates to Gemini API models including Gemini 2.5, 2.5 Lite, and various future/preview models (Gemini Deep Research, Antigravity Agent, Gemini Embedding variants) and notes on deprecation, endpoints, and recommended latest models (3.5 Flash-Lite, 3.8 Flash).
Perplexity Agent API web_search presets low/medium/high now default to search_type: "fast"; cost per 1,000 calls drops from $2.50 to $1 and latency ~800 ms reduction; xhigh remains standard search.
Gemini 4 Argon is now available for everyone.
Web search API pricing per 1,000 searches | looot.
Google's Custom Search JSON API is closed to new customers; Google’s own page says existing customers have until January 1, 2027 to move, and Vertex AI Search is the suggested alternative. Microsoft Bing Search APIs retired August 11, 2025 and decommissioned existing instances.
Parallel’s official Search API page now documents the selected fast-search mode as “fast” rather than “turbo” in the previous snapshot. Because search modes are part of the API’s endpoint behavior and system record, this is a material mode-naming or configuration change requiring verification in the provider…
Parallel materially changed its Search API offering: the fast search mode is now labeled “turbo” instead of “basic,” and the displayed cost decreased from $5 to $1 per 1,000 requests. The page continues to describe multiple search modes with different latency/depth tradeoffs, making this a material pricing and…
Openbenchmarks materially updated its independent web-search evaluation board on September 15. The update added Nimble lite and standard configurations across company-news, coding-agent, and multi-turn search benchmarks, plus You.com highlights with and without knowledge=core. The board now reports You highlights at…
Parallel materially updated its Search API offering with four search modes: Turbo at about 200 ms and $1 per 1,000 requests, Fast at about 700 ms and $1 per 1,000, Basic at about 1 second and $5 per 1,000, and Advanced at about 3 seconds and $5 per 1,000. The page also states a 600-requests-per-minute limit and…
Perplexity published a major Advanced Deep Research update. The system now searches more sources, cross-references information, processes uploaded documents, runs calculations through an improved code sandbox, and browses harder-to-reach web sources. It also adds clarifying questions, follow-up questions during…
keenable.ai (read 2026-08-26): Agent Builder tier $4 / 1000 requests; Frontier tier $1 / 1000 requests at 100 RPS+; <250 ms p95 (US East); 100B+ documents.
Research guide (read 2026-08-26): research_effort frontier at $1,200 per 1k calls, background=true required (sync → 422), 30 s–12,000 s with p50 300 s. Other tiers: lite $12, standard $50, deep $100, exhaustive $450 per 1k. Not wired in the arena.
OpenAI's deprecations page (read 2026-08-26) has no deep-research entry. The 2026-12-11 shutdown announced 2026-06-11 covers o3-2025-04-16, o3-pro-2025-06-10 and gpt-5-*-2025-08-07 snapshots → gpt-5.6-sol / terra / luna. gpt-5.5-pro is live at $30 / $180 per 1M. research.site's earlier “o3-deep-research retires 2026-12-11” item was wrong and is withdrawn.
Changelog 2026-08-24: citations and confidence scores are now emitted per list element (separate FieldBasis entries) instead of once per field, without the beta header.
OpenAI changelog 2026-08-21: gpt-5.6-sol pricing updated to $4.00 / 1M input and $20.00 / 1M output.
Changelog 2026-08-21: Search API mode "fast" at $1 per 1,000 requests with ~700 ms average latency; Turbo mode (2026-07-13) is $1 per 1,000 with p50 250 ms; basic / advanced stay $5 per 1,000. Task API processor prices unchanged ($5 lite → $2,400 ultra8x per 1k runs).
Changelog 2026-07-21: Responses API for latency-sensitive use, 5–60 s response times, structured outputs and full citations; synchronous, alongside the async Task API.
One GPT-6 Astra agent, five web tool stacks. Exa and built-in web tie at 11/26 on LiveBrowseComp, with Keenable one answer behind. Explore accuracy, run duration, and every public task verdict.
Claude Code vs Codex CLI under three search backends (builtin, Exa MCP, Valyu MCP) on a frozen 30-task LiveBrowseComp subset. claude-exa wins at 60%; the search backend moves accuracy up to 33 points, the agent at most 7.
Five deep-research APIs plus a Perplexity calibration anchor on a frozen 30-task ResearcherBench subset. Coverage is a three-way race; faithfulness splits the field in two; parallel has the best overall profile.
Nine deep research APIs on a frozen 20-task subset of DeepResearch-Bench-II. Exa effort tiers against each other, then one flagship tier per provider.
