How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Parallel Tasks API

The Task API executes web research and extraction tasks. Clients submit a natural-language objective with an optional input schema; the service plans retrieval, fetches relevant URLs, and returns outputs that conform to a provided or inferred JSON schema. Supports deep research style queries and can return rich structured JSON outputs. Processors trade-off between cost, latency, and quality. Each processor supports calibrated confidences.- Output metadata: citations, excerpts, reasoning, and confidence per fieldTask Groups enable batch execution of many independent Task runs with group-level monitoring and failure handling.- Submit hundreds or thousands of Tasks as a single group- Observe group progress and receive results as they complete- Real-time updates via Server-Sent Events (SSE)- Add tasks to an existing group while it is running- Group-level retry and error aggregation

Parallel Tasks API is one of 8 APIs that Parallel publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Task. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, a getting-started guide, and authentication docs.

This API exposes 12 operations across 11 paths, and defines 33 schemas. It is described by OpenAPI 3.1.0, at version 0.1.2.

Requests are made against a single base URL, https://api.parallel.ai.

12 operations 11 paths 33 schemas 9 GET3 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.1.0
API Version
0.1.2
Base URL
https://api.parallel.ai
Authentication
API Key
Resource Areas
1

Authentication & Security 1

Parallel Tasks API declares 1 security scheme for authenticating requests. An API key is passed in the header as x-api-key (ApiKeyAuth). By default, every request must be authenticated.

Paths & Operations 12

Across 11 paths, the API surfaces 12 operations — 9 GET, 3 POST. Each is listed below with its method, path, parameters, and response codes.

Tasks 12

The Task API executes web research and extraction tasks. Clients submit a natural-language objective with an optional input schema; the service plans retrieval, fetches relevant U…

POST
/v1/tasks/groups
Create Task Group
tasks_taskgroups_post_v1_tasks_groups_post body → 200422
GET
/v1/tasks/groups/{taskgroup_id}
Retrieve Task Group
tasks_taskgroups_get_v1_tasks_groups__taskgroup_id__get 1 param → 200422
GET
/v1/tasks/groups/{taskgroup_id}/events
Stream Task Group Events
tasks_sessions_events_get_v1_tasks_groups__taskgroup_id__events_get 3 params → 200404422
POST
/v1/tasks/groups/{taskgroup_id}/runs
Add Runs to Task Group
tasks_taskgroups_runs_post_v1_tasks_groups__taskgroup_id__runs_post 3 params body → 200422
GET
/v1/tasks/groups/{taskgroup_id}/runs
Fetch Task Group Runs
tasks_taskgroups_runs_get_v1_tasks_groups__taskgroup_id__runs_get 5 params → 200404422
GET
/v1/tasks/groups/{taskgroup_id}/runs/{run_id}
Retrieve Task Group Run
tasks_taskgroups_runs_id_get_v1_tasks_groups__taskgroup_id__runs__run_id__get 2 params → 200401404422
POST
/v1/tasks/runs
Create Task Run
tasks_runs_post_v1_tasks_runs_post 1 param body → 202401402403422429
GET
/v1/tasks/runs/{run_id}
Retrieve Task Run
tasks_runs_get_v1_tasks_runs__run_id__get 1 param → 200401404422
GET
/v1/tasks/runs/{run_id}/events
Stream Task Run Events
tasks_runs_events_get_v1_tasks_runs__run_id__events_get 1 param → 200401404422
GET
/v1/tasks/runs/{run_id}/input
Retrieve Task Run Input
tasks_runs_input_get_v1_tasks_runs__run_id__input_get 1 param → 200401404422
GET
/v1/tasks/runs/{run_id}/result
Retrieve Task Run Result
tasks_runs_result_get_v1_tasks_runs__run_id__result_get 3 params → 200401404408422
GET
/v1beta/tasks/runs/{run_id}/events
Stream Task Run Events
tasks_runs_events_get_v1beta_tasks_runs__run_id__events_get 1 param → 200401404422

Schemas 33

The contract defines 33 schemas that model the data the API accepts and returns. The most detailed are TaskRun (11 properties), TaskRunInput (10 properties), TaskRunJsonOutput (6 properties), McpToolCall (6 properties). Each schema is shown below with its type and property counts.

AutoSchema
object
Auto schema for a task input or output.
1 property
TaskGroupRunRequest
object
Request to initiate new task runs in a task group.
2 properties 1 required
TaskGroupStatusEvent
object
Event indicating an update to group status.
3 properties 3 required
TaskRunProgressStatsEvent
object
A progress update for a task run.
3 properties 3 required
TaskGroupStatus
object
Status of a task group.
5 properties 5 required
HTTPValidationError
object
1 property
TaskRunTextOutput
object
Output from a task that returns text.
5 properties 3 required
ParallelBeta
Model for the parallel-beta header.
McpServer
object
MCP server configuration.
5 properties 2 required
TaskGroupResponse
object
Response object for a task group, including its status and metadata.
4 properties 3 required
TaskRunProgressMessageEvent
object
A message for a task run progress update.
3 properties 3 required
TaskRunInput
object
Request to run a task.
10 properties 2 required
FieldBasis
object
Citations and reasoning supporting one field of a task output.
4 properties 2 required
TaskSpec
object
Specification for a task. Auto output schemas can be specified by setting outputschema={"type":"auto"}. Not specifying a TaskSpec is the same as setting an aut…
2 properties 1 required
Error
object
An error message.
3 properties 2 required
TaskRunResult
object
Result of a task run.
2 properties 2 required
Citation
object
A citation for a task output.
3 properties 1 required
ValidationError
object
3 properties 3 required
TaskRun
object
Status of a task run.
11 properties 7 required
Warning
object
Human-readable message for a task.
3 properties 2 required
ErrorResponse
object
Response object used for non-200 status codes.
2 properties 2 required
TaskRunEvent
object
Event when a task run transitions to a non-active status. May indicate completion, cancellation, or failure.
5 properties 3 required
TextSchema
object
Text description for a task input or output.
2 properties
Webhook
object
Webhooks for Task Runs.
2 properties 1 required
ErrorEvent
object
Event indicating an error.
2 properties 2 required
CreateTaskGroupRequest
object
Request to create a task group.
1 property
SourcePolicy
object
Source policy for web search results. This policy governs which sources are allowed/disallowed in results.
3 properties
JsonSchema
object
JSON schema for a task input or output.
2 properties 1 required
TaskRunJsonOutput
object
Output from a task that returns JSON.
6 properties 3 required
TaskRunSourceStats
object
Source stats for a task run.
3 properties 3 required
TaskAdvancedSettings
object
Advanced search configuration for a task run.
1 property
TaskGroupRunResponse
object
Response from adding new task runs to a task group.
4 properties 4 required
McpToolCall
object
Result of an MCP tool call.
6 properties 4 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

parallel-tasks-api-openapi.yml Raw ↑

Other APIs Parallel publishes across the network.

Parallel Chat API (Beta) API
Parallel Extract API
Parallel FindAll API
Parallel Monitor API
Parallel Search API
Parallel Responses API
Parallel Memory API
Where this information came from

This is an independent, third-party profile of Parallel Tasks API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.