Parallel
About[About](https://parallel.ai/about)Blog[Blog](https://parallel.ai/blog)Docs[Docs](https://docs.parallel.ai/introduction/quickstart)
Start Building
P
[Start Building](https://platform.parallel.ai/)
[Menu]

# Query the web like a database

## Get the highest quality structured data and insights from the open web

 

## A web API built with, by, and for AIs

Powering the next wave of apps, agents, and workflows

### Declarative

Specify what you want, get structured JSON back.

### Elastic

Flex accuracy, latency, and cost. Scale without constraints.

### Trusted

SOC-II Type 2 Certified, trusted by the most ambitious companies and enterprises.

Highest quality at every price point

State of the art across several benchmarks

BrowseComp WISER-AtomicSimpleQA
020040060080010001200Cost (CPM)0510152025303540450,0BASE3% / 10CPMCORE7% / 25CPMPRO17% / 100CPMULTRA27% / 300CPMPARALLEL 60039% / 600CPMPARALLEL 120048% / 1200CPMGPT-4.1 W/ BROWSING2% / 53CPMCLAUDE SONNET 4 W/ SEARCH6% / 1168CPMEXA RESEARCH14% / 275CPMPERPLEXITY DEEP RESEARCH8% / 880CPM

COST (CPM)

ACCURACY (%)

CPM: USD per 1000 requests. Cost is shown on a Linear scale.

Parallel
Others

### About the benchmark

This benchmark, created by OpenAI, contains 1,266 questions requiring multi-hop reasoning, creative search formulation, and synthesis of contextual clues across time periods. Read our blog here[here]($https://parallel.ai/blog/deep-research).

### Steps of reasoning

100% Multi-Hop questions

### Parallel 600/1200

Parallel 600 and 1200 are agents with the same architecture as Parallel Ultra (which costs 300 USD for 1000 queries), but with 2x and 4x the compute and cost.

## Highest quality at every price point

State of the art across several benchmarks

### BrowseComp Scaled Compute Benchmark

| Model                     | Cost (CPM) | Accuracy  (%) |
| ------------------------- | ---------- | ------------- |
| Base                      | 10         | 4             |
| Core                      | 25         | 7             |
| Pro                       | 100        | 17            |
| Ultra                     | 300        | 27            |
| Parallel 600              | 600        | 39            |
| Parallel 1200             | 1200       | 48            |
| GPT-4.1 w/ browsing       | 53         | 1             |
| Claude Sonnet 4 w/ search | 1168       | 6             |
| Exa Research              | 275        | 14            |
| Perplexity Deep Research  | 880        | 8             |

CPM: USD per 1000 requests. Cost is shown on a Linear scale.

### About the benchmark

This benchmark, created by OpenAI, contains 1,266 questions requiring multi-hop reasoning, creative search formulation, and synthesis of contextual clues across time periods. Read our blog here[here]($https://parallel.ai/blog/deep-research).

### Steps of reasoning

100% Multi-Hop questions

### Parallel 600/1200

Parallel 600 and 1200 are agents with the same architecture as Parallel Ultra (which costs 300 USD for 1000 queries), but with 2x and 4x the compute and cost.

### WISER-Atomic

| Model          | Cost (CPM) | Accuracy (%) |
| -------------- | ---------- | ------------ |
| Core           | 25         | 77           |
| Base           | 10         | 75           |
| Lite           | 5          | 64           |
| o3             | 45         | 69           |
| 4.1 mini low   | 25         | 63           |
| gemini 2.5 pro | 36         | 56           |
| sonar pro high | 16         | 64           |
| sonar low      | 5          | 48           |

CPM: USD per 1000 requests. Cost is shown on a Log scale.

### About the benchmark

This benchmark, created by Parallel, contains 121 questions intended to reflect real-world web research queries across a variety of domains. Read our blog here[here]($https://parallel.ai/blog/parallel-task-api).

### Steps of reasoning

50% Multi-Hop questions
50% Single-Hop questions

### Distribution

40% Financial Research
20% Sales Research
20% Recruitment
20% Miscellaneous

### SimpleQA

| Model            | Cost (CPM) | Accuracy (%) |
| ---------------- | ---------- | ------------ |
| Lite             | 5          | 92           |
| Base             | 10         | 94           |
| Core             | 25         | 94           |
| o3 high          | 56         | 92           |
| 4.1 mini high    | 30         | 88           |
| gemini 2.5 flash | 35         | 91           |
| sonar            | 8          | 81           |
| sonar pro        | 13         | 84           |

CPM: USD per 1000 requests. Cost is shown on a Log scale.

### About the benchmark

This benchmark contains 4,326 questions focused on short, fact-seeking queries across a variety of domains. Read our blog here[here]($https://parallel.ai/blog/parallel-task-api).

### Steps of reasoning

100% Single-Hop questions

### Distribution

36% Culture
20% Science and Technology
16% Politics
28% Miscellaneous

## Task API

Highest quality web enrichment & research for repeatable workloads

Task playground[Task playground](https://platform.parallel.ai/play)
TthenP
ID
Entities
Product releases
SOC 2 status
1
2
3
4
5
6
7

## Chat API

Low-latency chat completions API for interactive applications

Chat playground[Chat playground](https://platform.parallel.ai/play/chat)
CthenP
Ask anything...

## Search API

The best search and extract interfaces for AI agents to query the web

Search Playground [Search Playground ](https://platform.parallel.ai/play/search)
SthenP

Start building

## The web, organized for AIs

Parallel is building new interfaces for AI to work with the web

API Platform
P
[API Platform](https://platform.parallel.ai)

Latest updates

June 17

[State of the Art Deep Research APIs](https://parallel.ai/blog/deep-research)

State of the art results on the BrowseComp benchmark

Tags:Benchmarks
June 10

[Introducing the Parallel Search API ](https://parallel.ai/blog/parallel-search-api)

A new low level tool for your AI Agent to access the web

Tags:Product Release
May 16

[Introducing Basis with Calibrated Confidences ](https://parallel.ai/blog/introducing-basis-with-calibrated-confidences)

Citations, reasoning, excerpts, and confidences with each output

Tags:Product Release
![Company Logo](https://parallel.ai/parallel-logo-540.png)

Company

  • hello@parallel.ai[hello@parallel.ai](mailto:hello@parallel.ai)

Resources

  • About[About](https://parallel.ai/about)
  • Docs[Docs](https://docs.parallel.ai)
  • Blog[Blog](https://parallel.ai/blog)
  • Careers[Careers](https://jobs.ashbyhq.com/parallel)

Info

  • Terms[Terms](https://parallel.ai/terms-of-service)
  • Privacy[Privacy](https://parallel.ai/privacy-policy)
  • Trust Center[Trust Center](https://trust.parallel.ai/)
LinkedIn[LinkedIn](https://www.linkedin.com/company/parallel-web/about/)

Parallel Web Systems Inc. 2025