Priced like infrastructure, not like a research tool
Every plan gets the same evidence layer — ground, the coverage receipts, every MCP tool and the whole coverage graph. What changes is volume, rate and how far back you can reach.
Verified 15 September 2026·Plans mirror the billing service
Free
$0 forever
$0
- 10,000 credits / month
- 60 credits / minute
- 30 days of history
- All 13 billed endpoints and 13 MCP tools
- ground, coverage receipts, the full coverage graph
- Stops at its monthly credits
Building, evaluating, and side projects that stay small.
Start freeBuild
For a product in production
$29/month
$0.58 per 1,000 credits
- 50,000 credits / month
- 600 credits / minute
- 1 year of history
- All 13 billed endpoints and 13 MCP tools
- ground, coverage receipts, the full coverage graph
- Then $1 per 1,000 credits
A live agent or app with real users.
Choose BuildScale
For high-volume agent traffic
$199/month
$0.40 per 1,000 credits
- 500,000 credits / month
- 3,000 credits / minute
- 5 years of history
- All 13 billed endpoints and 13 MCP tools
- ground, coverage receipts, the full coverage graph
- Then $0.60 per 1,000 credits
Agent fleets and multi-tenant products.
Choose ScaleArchive
Everything, all the way back
$799/month
$0.40 per 1,000 credits
- 2,000,000 credits / month
- 12,000 credits / minute
- Full archive
- All 13 billed endpoints and 13 MCP tools
- ground, coverage receipts, the full coverage graph
- Then $0.40 per 1,000 credits
Research, monitoring and longitudinal analysis.
Choose ArchiveA search costs 1 credit, so a price per 1,000 credits is also a price per 1,000 searches. The credits-a-minute figure is counted once for the whole account, so it is the rate you actually get. Prices in USD, billed monthly. Changing plan applies to every live key on the account in one operation.
The free tier is generous on volume and slow on purpose
10,000 credits a month — that many searches — is the largest free tier in the category: twice Parallel's 5,000, ten times Tavily's 1,000, and a standing allowance where Exa and Brave give a monthly dollar credit. We can afford it because a cached query costs us almost nothing, and we need it because you cannot evaluate a search index properly on a thousand queries.
The constraint is the rate limit instead: 60 credits a minute, which is a search a second or a ground call every 5 seconds. That is ample for building, testing and running an evaluation set, and not enough to serve real users — so the tier you outgrow is the one you outgrow on latency, not on a surprise bill. It hard-caps at its monthly credits rather than billing you.
What a call costs
Allowances are in credits, and every call has a fixed price in them — set by what the call does, known before it runs, and the same over HTTP and MCP. A search is 1 credit; ground, which returns a whole evidence set with its receipt, is 5 credits however many stories it expands.
| Call | HTTP | MCP tool | Credits |
|---|---|---|---|
| Search | GET /search | web_search | 1 |
| Fetch a document | GET /doc/{id} | get_document | 1 |
| Similar passages | GET /similar | similar | 1 |
| Browse a topic | GET /browse | browse | 1 |
| Why a URL is or is not present | GET /why_not | why_not | 1 |
| Hosts carrying one story | GET /corroborate | corroborate | 2 |
| Related passages and stories | GET /related | related | 2 |
| Authorities on a topic | GET /authorities | authorities | 2 |
| Brief on an entity | GET /dossier | dossier | 2 |
| Connection between two nodes | GET /path | path | 2 |
| Budget-packed reading set | GET /assemble_context | assemble_context | 3 |
| Evidence set with a coverage receipt | GET /ground | ground | 5 |
| What changed in the evidence | GET /changes | evidence_changes | 10 |
| Your plan and usage | GET /account | — | 0 |
- A call that runs and fails costs 1 credit, whatever it would have cost.
- A refused call costs nothing. A 401, 402 or 429 never ran anything. A hard-capped key refuses a call it cannot afford in full rather than run it.
- Connecting is free. The MCP handshake — initialize, notifications, tools/list and ping — /account, and the unauthenticated descriptions such as /describe are never billed.
- The rate limit is in credits too. A call takes its cost from the minute, so the free tier's 60-credit minute is 60searches or 12 ground calls.
- Every charge is visible. Each response carries x-credits-charged, /describe lists this table, and every operation in the OpenAPI document carries its cost as x-credits.
What a workload costs
A price per call is the wrong unit for an agent: a task makes several calls, and what you pay is per task. Here is each published workload at three volumes, on whichever plan is cheapest for it. Your model and the people who review its answers are separate lines —cost per completed taskshows how to measure all three.
| Workload, per task | Credits | 1,000 tasks/mo | 10,000 tasks/mo | 100,000 tasks/mo |
|---|---|---|---|---|
| Grounded answer1 ground | 5 | $29Build | $29Build | $199Scale |
| RAG pipeline1 assemble_context + 1 search + 1 corroborate | 6 | $29Build | $39Build + overage | $259Scale + overage |
| Research agent1 authorities + 1 dossier + 2 related + 1 path | 10 | $29Build | $79Build + overage | $499Scale + overage |
| Claim checking1 search + 2 corroborate + 1 authorities | 7 | $29Build | $49Build + overage | $319Scale + overage |
| News monitoring1 browse + 2 search + 1 corroborate | 5 | $29Build | $29Build | $199Scale |
| Competitive intelligence1 dossier + 1 path + 1 related + 2 search | 8 | $29Build | $59Build + overage | $379Scale + overage |
| Coding agent lookups2 search + 1 doc | 3 | $29Build | $29Build | $199Scale |
| Question answering1 assemble_context + 1 corroborate | 5 | $29Build | $29Build | $199Scale |
| Compliance research2 search + 1 assemble_context + 1 why_not | 6 | $29Build | $39Build + overage | $259Scale + overage |
| Content discovery2 similar + 1 related + 1 search | 5 | $29Build | $29Build | $199Scale |
| Multilingual retrieval2 search + 1 assemble_context | 5 | $29Build | $29Build | $199Scale |
Monthly provider spend on the cheapest paid plan for that volume, overage included — the free tier is for building and evaluating, and its rate limit is set accordingly. Each pattern mirrors the recipe on its use-case page and is illustrative, not measured — your agent’s real pattern is what an evaluation records.
How that compares
- SerpAPI · Starter plan63×$25
SerpApi pricing, read 7 October 2026
Gemini API pricing, read 7 October 2026
Brave Search API pricing, read 7 October 2026
- Exa · Instant search10×$4
Exa pricing, read 7 October 2026
Parallel pricing, read 7 October 2026
- unlob — Scale$0.40
| Provider | Own index? | $ / 1,000 searches | Source |
|---|---|---|---|
Priced: Starter plan. $25 per 1,000 searches on the Starter plan ($25 a month for 1,000), falling to about $1.96 per 1,000 on the largest Cloud plan. | No Scrapes Google, Bing, Baidu and others | $25 | SerpApi pricing |
Priced: search queries on Gemini 3.x. $14 per 1,000 search queries on Gemini 3.x models after 5,000 free search requests a month (paid tier, shared across Gemini 3.x), plus model token charges. One prompt can trigger several billed queries. Gemini 2.5 models keep the older scheme: $35 per 1,000 grounded prompts after 1,500 free a day. | Yes Google's index | $14 | Gemini API pricing |
Priced: Grounding with Bing Search transactions (one per tool call). $14 per 1,000 transactions, counted per tool call within an agent run, with model costs billed separately. Available only inside Azure AI Foundry Agent Service or as a web knowledge source in Azure AI Search, and the raw results are not returned to the developer. | Yes Bing index, via Azure AI Foundry | $14 | Grounding with Bing Search |
TavilyAcquired Priced: basic search, pay as you go. Credit-based at $0.008 per credit pay-as-you-go. A basic search is 1 credit (~$8 per 1,000), an advanced search 2 credits (~$16 per 1,000), and a research request 4 to 250 credits. Fast and ultra-fast searches are also 1 credit; monthly plans bring the effective rate down to $5 per 1,000 at 100,000 credits ($500 a month). | No No publicly documented independent web index | $8 | Tavily pricing |
Priced: Search plan. Search is $5 per 1,000 requests. The Answers plan is $4 per 1,000 plus $5 per million tokens. | Yes 40B+ pages, no Google or Bing dependency | $5 | Brave Search API pricing |
Priced: standard-depth search. $5 per 1,000 standard-depth searches returning results ($0.005 a call); $6 per 1,000 with a sourced answer, and $50 per 1,000 at deep depth. | Partial Own retrieval layer over partner and web sources | $5 | Linkup pricing |
Priced: paid queries (existing customers only). $5 per 1,000 queries after 100 free a day, up to 10,000 queries a day — for existing customers only. The API is closed to new customers and is discontinued on 1 January 2027. | Yes Google's index, via Programmable Search Engine | $5 | Custom Search JSON API pricing |
Priced: Instant search. Instant search is $4 per 1,000 requests (up to 10 results); Fast and Auto are $7 per 1,000, and the Deep modes $12 to $15. Results beyond 10 add $1 per 1,000, contents $1 per 1,000 pages per content type, and AI summaries $1 per 1,000 pages — so a realistic RAG call costs more than the headline. | Yes Proprietary AI-native semantic index | $4 | Exa pricing |
Priced: SERP API, pay as you go. The SERP API returns scraped search-engine results pages at $1.50 per 1,000 requests pay as you go; the $499-a-month Scale plan includes 380,000 requests, then $1.30 per 1,000. Proxy and browser products are priced per GB. | No Proxy, unblocking and scraping infrastructure | $1.50 | Bright Data SERP API pricing |
Priced: Turbo processor. The Turbo and Fast search processors are $1 per 1,000; Basic and Advanced are both $5 per 1,000. The Task API, which is what most agent workloads actually use, runs $5 to $2,400 per 1,000 depending on processor. | Yes Proprietary web index and retrieval infrastructure | $1 | Parallel pricing |
Priced: Starter credit pack. $1 per 1,000 on the Starter credit pack, falling to $0.30 per 1,000 on the largest pack. Prepaid credits, valid for six months. | No Google SERP wrapper | $1 | Serper pricing |
Priced: Search API with Fast Search. The Search API is $5 per 1,000 requests, or $1 with Fast Search, with no token charges (up to 20 results, 10 by default). Sonar Chat Completions support ended on 27 September 2026 and requests are moving to the Agent API; Sonar charged $5 to $12 per 1,000 by search context size plus $1/$1 per million tokens, and Sonar Pro $6 to $14 plus $3/$15. | Yes Perplexity index | $1 | Perplexity API pricing |
Priced: Standard queue (asynchronous). $0.60 per 1,000 SERPs (10 results each) in the Standard queue, which is asynchronous: you post a task and collect the result later. Priority queue is $1.20 per 1,000 and real-time Live mode $2. Pay as you go, with a $50 minimum payment. | No SERP data collection at scale | $0.60 | DataForSEO SERP API pricing |
$29 per month for 50,000 credits, and a search is one credit. | Yes Our own crawl and index | $0.58 | This page |
$199 per month for 500,000 credits, and a search is one credit. | Yes Our own crawl and index | $0.40 | This page |
The full 2026 landscape, including funding and index ownership →
Frequently asked questions
What does a call cost?
Calls are priced in credits by what they do: a search, a document fetch, similar, browse and why_not cost 1 credit; corroborate, related, authorities, dossier and path 2; assemble_context 3; ground 5; changes 10. A call that runs and fails costs 1 credit, and a refused call — a 401, 402 or 429 — costs nothing. /account, the MCP handshake, health probes, the capability catalog at /describe, the skill and the machine-readable descriptions are free. Every response says what it charged in an x-credits-charged header.
What happens when I run out of credits?
On the free tier, calls stop — it hard-caps, because there is no card on file and a surprise bill is worse than a clear stop. A call that would cost more than the credits you have left is refused with a 429 rather than run, so an expensive call cannot overshoot the allowance. On paid plans you keep serving, and credits past the allowance are billed at $1.00 on Build, $0.60 on Scale and $0.40 on Archive per 1,000 credits.
What does "history" mean on each plan?
It is how far back that tier may query. Free reaches 30 days, Build a year, Scale five years, and Archive the full index with no date floor. It bounds the date range of your filters, not the freshness of results — every plan sees the newest content.
Is the rate limit per account or per server?
Per account, once. Your plan's rate — 60 credits a minute on Free up to 12,000 on Archive — is counted in a single window for the whole account, however many machines answer your requests. So the published number is the number you get, not a floor with undocumented headroom above it. Exceed it and the call is refused with a 429 whose retry-after says how many seconds are left in that minute; sleep that value rather than a fixed second.
Do you have an enterprise plan?
Archive at $799 a month covers 2,000,000 credits, 12,000 credits a minute and the full archive, which handles most workloads that would elsewhere be called enterprise. If you need more than that, or committed capacity, get in touch. If you need the evidence layer inside your own boundary — a national cloud, your VPC, or a disconnected environment — that is the sovereign edition: the same product, deployed and scoped per installation, and priced per installation rather than per credit. It is not on this table on purpose.
Can I change plans or cancel?
Yes, from the console at any time. Changes apply to every live key on the account in one operation, so you never have a window where some keys are on the old plan.
How is this so much cheaper than the alternatives?
Because the structure is precomputed. Story clusters, origins, the link graph and the corroboration signals are built when the index is built, so a ground call is retrieval over stored structure rather than a research agent spending model inference on every question — it costs infrastructure money, not research-agent money. We also own the index, so no part of our bill is a per-query fee to an upstream provider, and what we spend follows how much the API is used rather than how large the index is. The cost model page sets out the full argument.
Start with 10,000 free credits
No card required. The same magic link creates your unlob account and issues your first API key.
Evaluating for a team or at volume? Send a workload brief or write to hello@unlob.com — a person replies.