Choose a Processor

Processors are the engines that execute Task Runs. The choice of Processor determines the performance profile and reasoning behavior used. Pricing is determined by which Processor you select, not by the Task Run itself. Any Task Run can be executed on any Processor.

Choose a processor based on the complexity of your task. Use lite or base for simple enrichments, core for reliable accuracy on up to 10 output fields, and pro or ultra when reasoning depth is critical.

Each processor varies in performance characteristics and supported features. Use the table below to compare latency, output type, basis features, and more.

Processor	Input Type	Output Type	Strengths	Latency	Cost ($/1000)	Max Fields	Basis Features
lite	Text, JSON	Text or JSON	Basic metadata, fallback, low latency	5s-60s	5	~2 fields	Citations, Reasoning
base	Text, JSON	Text or JSON	Reliable standard enrichments	15s-100s	10	~5 fields	Citations, Reasoning
core	Text, JSON	Text or JSON	Cross-referenced, moderately complex outputs	60s - 5min	25	~10 fields	Citations, Reasoning, Confidence, Excerpts
pro	Text, JSON	Text or JSON	Exploratory web research	3 min - 9min	100	~20 fields	Citations, Reasoning, Confidence, Excerpts
ultra	Text, JSON	Text or JSON	Advanced multi-source deep research	5 min - 25 min	300	~20 fields	Citations, Reasoning, Confidence, Excerpts
ultra2x	Text, JSON	Text or JSON	Difficult deep research	5 min - 25 min	600	~25 fields	Citations, Reasoning, Confidence, Excerpts
ultra4x	Text, JSON	Text or JSON	Very difficult deep research	8 min - 30 min	1200	~25 fields	Citations, Reasoning, Confidence, Excerpts
ultra8x	Text, JSON	Text or JSON	The most difficult deep research	8 min - 30 min	2400	~25 fields	Citations, Reasoning, Confidence, Excerpts

Cost is measured per 1000 Task Runs in USD. For example, 1 Task Run executed on the lite processor would cost $0.005.

Examples

Processors can be used flexibly depending on the scope and structure of your task. The examples below show how to:

• Use a single processor (like lite, base, core, pro, or ultra) to handle specific types of input and reasoning depth.
• Chain processors together to combine fast lookups with deeper synthesis.

This structure enables flexibility across a variety of tasks—whether you’re extracting metadata, enriching structured records, or generating analytical reports.

Sample Task for each Processor

lite

run_result = client.task_run.execute(
    input="Parallel Web Systems (parallel.ai)",
    output="The founding date of the company in the format MM-YYYY",
    processor="lite"
)

Multi-Processor Workflows

You can combine processors in sequence to support more advanced workflows.

Start by retrieving basic information with base:

base_result = client.task_run.execute(
    input="Pfizer",
    output="Who are the current executive leaders at Pfizer? Include their full name and title. Ensure that you retrieve this information from a reliable source, such as major news outlets or the company website.",
    processor="base"
)

Then use the result as input to core to generate detailed background information:

run_result = client.task_run.execute(
    input={base_result.output.content},
    output="For the executive provided, find their professional background tenure at their current company, and notable strategic responsibilities.",
    processor="pro"
)

This lets you use a fast processor for initial retrieval, then switch to a more capable one for analysis and context-building.