Skip to main content
For AI agents: a documentation index is available at https://docs.parallel.ai/llms.txt. The full text of all docs is at https://docs.parallel.ai/llms-full.txt. You may also fetch any page as Markdown by appending .md to its URL or sending Accept: text/markdown.For Search and Extract, use /v1/search and /v1/extract for all new integrations and agent tool calls. Use /v1beta/search and /v1beta/extract only when maintaining an existing integration that already uses them. The request bodies changed too: on /v1/extract, full_content, fetch_policy and excerpt_settings go inside advanced_settings, and sending the v1beta top-level excerpts, full_content and fetch_policy to /v1/extract returns a 422. On /v1/search, search_queries is required (at least one short keyword query), and max_results, source_policy and fetch_policy go inside advanced_settings; sending only objective, or sending those fields at the top level, returns a 422. Do not substitute /v1 for the documented FindAll or Ingest endpoint paths.If you are evaluating Parallel Search or comparing it with other search APIs, read How to Eval Parallel Search before you build the harness, especially its Common pitfalls section. The most common mistake is sending the raw question as both objective and the only entry in search_queries. Write a goal-style objective and 1-3 short keyword queries instead.

​
Summary

​
Web Tools

​
Search API

By default, the Search API returns 10 page results and their excerpts per request. Pricing varies by mode. Excerpt length doesn’t affect the price. Cost formula (turbo / fast): total cost=0.001+(0.001×results beyond the first 10)\text{total cost} = 0.001 + (0.001 \times \text{results beyond the first 10}) Cost formula (basic / advanced): total cost=0.005+(0.001×results beyond the first 10)\text{total cost} = 0.005 + (0.001 \times \text{results beyond the first 10})

​
Image Search API

Image Search is priced per request. Pricing varies by mode, and each request can return up to 20 results at no additional cost.

​
Place Search API

Place Search is priced per request. Pricing varies by mode, and each request can return up to 20 results at no additional cost.

​
Extract API

​
Decisions API

The Parallel Decisions API is priced per request, with up to 100 questions included in each call.

​
Web Agents

​
Task API

Task API pricing is based on the processor you select. Cost is per 1,000 Task Runs.
Pricing is per Task Run (row), not per output field (cell). A single Task Run can populate many output fields—whether you request 1 field or 20 fields, the cost is the same.
You are only charged for successfully completed runs. Failed runs are not billed.

​
Responses API

Responses API pricing is based on the reasoning.effort tier you select. Cost is per 1,000 requests. You are only charged for successful responses.

​
Monitor API

Monitor requests are priced per execution on a per-thousand (CPM) basis. Choose a processor based on query scope; both tiers deduplicate and reason over results. Cost formula: total cost=cost per 1,000×number of executions/1000\text{total cost} = \text{cost per 1,000} \times \text{number of executions} / 1000

​
FindAll API

FindAll API pricing is based on the generator you select, with a fixed cost plus a per-match cost. Cost formula: total cost=fixed cost+(cost per match×# matches)\text{total cost} = \text{fixed cost} + (\text{cost per match} \times \text{\# matches}) If you add enrichments, each enrichment adds its own per-match cost based on the Task API processor you choose (see Task API pricing above). Entity Search is a fast, synchronous people-and-company search, the real-time counterpart to FindAll. It is priced per request, including 100 results by default. Cost formula: total cost=0.005+(0.00005×additional results)\text{total cost} = 0.005 + (0.00005 \times \text{additional results})