> ## Documentation Index > Fetch the complete documentation index at: https://deepline.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Use Parallel in Deepline > Use paid REST search/extract for Plays, enrich, batches, repeated, unattended, or production work. Includes inputs, outputs, SDK V2 examples, and Deepline cost. [Human guide: work with your agent →](https://deepline.com/docs/human/providers/parallel/guide.md) Inspect one Parallel action before starting provider-backed work. Your first result is a verified input and output contract. ## Provider-specific requirements Use Parallel for managed research/extraction runs without custom orchestration. * Use `parallel_run_task`, `parallel_search`, and `parallel_extract` for agent-friendly workflows. * Use the paid REST actions `parallel_search` and `parallel_extract` for every Play, enrich, map, dataset, batch, repeated, unattended, or production workload. * The free anonymous `parallel_search_mcp` and `parallel_fetch_mcp` actions are exact-name tools for small, direct, one-off exploration only. They are intentionally omitted from general tool discovery. * Never put a free MCP action in a Play or scale loop. Use `parallel_search` or `parallel_extract` instead. * Prefer `parallel_search` first for attendee/discovery workflows, then `parallel_extract` for targeted pages. * `parallel_search_mcp` is only for an explicitly requested lightweight lookup where zero provider spend matters more than reliability or REST-side controls. * `parallel_fetch_mcp` is only for directly reading a small set of URLs during that same exploratory session. * Use `parallel_run_task` when you need synthesized, schema-shaped outputs from multiple sources. * Call `parallel_run_task` first. If it finishes quickly, use that result. * If `parallel_run_task` returns pending or times out, keep the `run_id` and use `parallel_get_task_run_result` later to fetch the final output. * Ignore `parallel_get_task_run` unless you specifically need run metadata like status timestamps or processor info. * Keep monitor/stream endpoints out of default flows unless a user explicitly needs them. * For larger or uncertain authorized research, pilot on a small objective before widening `max_results` and scope. Do not add a pilot or repeat approval for a small supplied Play. Inspect existing task results by `run_id`. inspection does not authorize a new paid research run or repair. The REST-only policy for Plays and scale still applies. * For a direct exploratory MCP call, pass a stable `session_id` across related calls when possible to reduce anonymous-tier throttling. A session id does not make MCP suitable for scale. ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline tools execute parallel_search --payload '{"mode":"agentic","objective":"Find recent hiring and launch signals for OpenAI","max_results":5,"excerpts":{"max_chars_per_result":1200,"max_chars_total":10000}}' ``` ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline tools execute parallel_search_mcp --payload '{"objective":"Find recent OpenAI product announcements","search_queries":["OpenAI recent announcements","site:openai.com/news OpenAI product"],"session_id":"demo-session"}' ``` ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline tools execute parallel_extract --payload '{"urls":["https://openai.com/research/index/release/"],"objective":"Extract key product launch signal, release summary, and source evidence","full_content":true}' ``` ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline tools execute parallel_fetch_mcp --payload '{"urls":["https://openai.com/news"],"objective":"Extract the latest product announcement headlines","search_queries":["OpenAI latest product announcements"],"session_id":"demo-session"}' ``` ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline tools execute parallel_run_task --payload '{"processor":"lite-fast","input":"Summarize key GTM signals for OpenAI from recent public web sources in 3 bullets."}' ``` ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline tools execute parallel_get_task_run_result --payload '{"run_id":"trun_123"}' ``` ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline tools execute parallel_search --payload '{"objective":"Find AI companies that raised Series A funding in 2024 with source links","max_results":10}' deepline tools execute parallel_extract --payload '{"urls":["https://techcrunch.com/2024/12/20/heres-the-full-list-of-49-us-ai-startups-that-have-raised-100m-or-more-in-2024/"],"objective":"Extract company name, funding round, amount, date, and source evidence","excerpts":true}' ``` ## Find an applicable action Confirm your effective workspace, then search the live catalog: ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline auth status --json deepline search "Parallel" --type tools --json ``` Search returns candidates. Check the returned provider and operation rather than selecting a similar title automatically. ## Inspect the selected contract Replace `` with the identifier returned by discovery: ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline describe --json ``` These commands do not execute the selected provider action. Read its required inputs, supported access mode, pricing unit, outputs, and limits. A connection does not establish that every action supports BYOK. Follow the provider-specific requirements above and the live action contract. ## Prepare one reviewed input Use one authorized record that matches the inspected schema. Preserve its source identity and define the result you will accept. Open the action reference for its payload and response shape. Provider-backed execution can incur usage or external effects. For reusable logic, follow [Write Plays](https://deepline.com/docs/sdk-v2/plays.md). For direct-call recovery, use [Tool execution recovery](https://deepline.com/docs/sdk-v2/tool-execution-recovery.md). > [!TIP] > > Continue only when the workspace, provider, required fields, acceptance rule, and applicable price are understood. Keep unavailable access separate from no-result evidence. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.