DELTA
Customer Stories
Delta uses Fathom to get the latest docs for more accurate code
Coding agents use Fathom for low-latency search across millions of repos.
Search the web for free
Run up to 25,000 queries every month at no cost
Get started
Use cases
Coding copilots
Chat assistants
News tracking
Data enrichment
Voice agents
People lookup
Company lookup
Starter
Run up to 25,000 queries every month for free
Free 25,000 queries / month
Starter
Free web search for early builders and side projects
Free 25,000 queries / month
- Search API calls for agents
- Page text and highlights
- Tunable latency: 200ms to 1s
Live Search
Real-time search data with token-efficient page contents
$8 / 1k queries
- Search API calls for agents
- Page text and highlights
- Tunable latency: 200ms to 1s
{
"name" :
"role" :
"founded" :
}
"name" :
"role" :
"founded" :
}
Deep Search
Research with structured outputs optimized for complex queries
$13–16 / 1k queries
- Multi-step agent workflows
- Answers with structured outputs
- Web-grounded citations
Agent
Async agents for deep research, list building, and enrichment
$0.015–$2.40 / run
- Asynchronous deep research runs
- Structured outputs with citations
- Beta access available now
Contents
Full page content extraction with highlights and summaries
$1 / 1k pages
- Token-efficient page contents
- Highlights and AI summaries
- Configurable crawl depth
Use cases
Coding copilots
Chat assistants
News tracking
Data enrichment
Voice agents
People lookup
Company lookup
Coding copilots
Search across millions of GitHub repos, docs, and Stack Overflow with high-accuracy code retrieval.
- Search docs, repos, and changelogs in real time
- Use sub-200ms search options inside latency-sensitive agent loops
- Ground code generation with current package and API references
Endpoint pricing
| Search | Deep Search | Deep-Reasoning Search | Contents | Monitors | Answer | |
|---|---|---|---|---|---|---|
| Base price, with up to 10 results (per 1k requests) | $8 | $13 | $16 | $1 (per 1k pages) | $16 | $6 |
| Cost per additional result above 10 (per 1k requests) | $1 | $1 | $1 | – | $1 | $1 |
| AI page summaries (per 1k pages) | $1 | $1 | $1 | $1 | $1 | $1 |
Agent pricing
By default, Agent uses effort: auto. Compute and tool usage scale to the task. Choose a fixed effort mode for predictable per-request pricing.
For request parameters, run lifecycle events, and examples, see the Agent docs.
Usage components
- Agent Compute Units $0.12 / ACU
- Search tool calls $0.006 / search
- Email contact enrichment $0.03 / email
- Phone contact enrichment $0.08 / phone number
Fixed effort modes*
- Minimal $0.015 / request
- Low $0.03 / request
- Medium $0.12 / request
- High $0.60 / request
- X-high $1.20 / request
*Contact enrichment for emails and phone numbers is billed separately.
Powerful search
- Up to 1,000 results per search
- Requests with more than 25 results
- Custom rate limits (QPS)
- Tailored moderation
- Custom index
Enterprise-Grade Support
- SLAs and MSAs
- 1:1 onboarding and support
- Zero Data Retention
Custom Pricing
- Volume discounts
- Standard billing
Startup and Education Grants
Build comprehensive web search into your startup or education project—for free.
$1,000 worth of free credits
Build, launch, and test search
Search built for your AI
The fastest, most accurate web search API. Give your agents the context they need.
Try the API for free