# 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
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]($https://parallel.ai/blog/deep-research).
### Steps of reasoning
100% Multi-Hop questions
### Parallel 600/1200
Parallel 600 and 1200 are agents with the same architecture as Parallel Ultra (which costs 300 USD for 1000 queries), but with 2x and 4x the compute and cost.
## Highest quality at every price point
State of the art across several benchmarks
### BrowseComp Scaled Compute Benchmark
| Model | Cost (CPM) | Accuracy (%) | | ------------------------- | ---------- | ------------- | | Base | 10 | 4 | | Core | 25 | 7 | | Pro | 100 | 17 | | Ultra | 300 | 27 | | Parallel 600 | 600 | 39 | | Parallel 1200 | 1200 | 48 | | GPT-4.1 w/ browsing | 53 | 1 | | Claude Sonnet 4 w/ search | 1168 | 6 | | Exa Research | 275 | 14 | | Perplexity Deep Research | 880 | 8 |
CPM: USD per 1000 requests. Cost is shown on a Linear scale.
### About the benchmark
This benchmark, created by OpenAI, contains 1,266 questions requiring multi-hop reasoning, creative search formulation, and synthesis of contextual clues across time periods. Read our blog here[here]($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
## Chat API
Low-latency chat completions API for interactive applications
## Search API
The best search and extract interfaces for AI agents to query the web
Start building
## The web, organized for AIs
Parallel is building new interfaces for AI to work with the web
Latest updates