Pricing # Pay as you go Run up to 5,000 requests per month for free | | Task API | Search API | Extract API | Responses API | Monitor API | Find All API | | ----------------- | --------------------------------------------------------- | ----------------------------------- | --------------------------------------- | ------------------------------------------------------------- | ------------------------------------------- | ----------------------------------------------- | | Inputs | Existing structured data, Question | Search objective, Keywords | URL, Extract objective | Question | Query, Frequency | Query | | Outputs | Deep research, Structured enrichments | Ranked URLs, Compressed excerpts | Full page contents, Compressed excerpts | Free text, Structured JSON | New events | Matches | | Best for | Deep research, database enrichment,or workflow automation | Web search tool calls for AI agents | URL content extraction | Latency-sensitive research in products and research subagents | Continuous monitoring of changes on the web | Finding all entities matching specific criteria | | Latency | 5s - 30min, asynchronous | 200ms - 3s, synchronous | < 3s, synchronous | 5s - 60s, synchronous | Asynchronous | 10min-1hr,asynchronous | | Basis | Citations, reasoning, confidence, excerpts | — | — | Citations | Citations | Citations, reasoning, confidence, excerpts | | Rate limits | 2,000 requests / min | 600 requests / min | 600 requests / min | 300 requests / min | 300 requests / min | 25 / hr | | Security | SOC2 | SOC2 | SOC2 | SOC2 | SOC2 | SOC2 | | Price per request | $0.005 - $2.4 | $0.001 - $0.005 for 10 results | $0.001 | $0.01 - $0.25 | $0.003-$0.01 | $0.03 - $1 per match | Earn up to $80 at signup + $5 in free credits per month ## Enterprise Built for scalable, reliable, enterprise workloads [Get a demo](https://contact.parallel.ai/) * Zero Data Retention (ZDR) * Data Protection Agreements * Single Sign-On * Zero Data Retention (ZDR) * Data Protection Agreements * Single Sign-On * Custom rate limits * Early access to new products * Dedicated onboarding and technical support * Custom rate limits * Early access to new products * Dedicated onboarding and technical support ## Allocate compute based on task complexity Parallel lets you easily flex compute based on the complexity of your task ## Pricing breakdown ### \### Task API | Processor | Cost (per 1K requests) | Best for | Latency | Max Fields | Basis | | --------- | ---------------------- | -------------------------------------- | ---------- | ---------- | ------------------------------------------ | | Lite | $5 | Basic information retrieval | 5s-60s | ~2 | Citations, Reasoning | | Base | $10 | Simple web research | 15s-100s | ~5 | Citations, Reasoning | | Core | $25 | Complex web research | 1min-5min | ~10 | Citations, Reasoning, Excerpts, Confidence | | Core2x | $50 | Very complex web research | 2min-5min | ~10 | Citations, Reasoning, Excerpts, Confidence | | Pro | $100 | Exploratory web research | 3min-9min | ~20 | Citations, Reasoning, Excerpts, Confidence | | Ultra | $300 | Extensive deep research | 5min-25min | ~20 | Citations, Reasoning, Excerpts, Confidence | | Ultra2x | $600 | Advanced deep research with 2x compute | 5min-25min | ~25 | Citations, Reasoning, Excerpts, Confidence | | Ultra4x | $1,200 | Advanced deep research with 4x compute | 8min-30min | ~25 | Citations, Reasoning, Excerpts, Confidence | | Ultra8x | $2,400 | Advanced deep research with 8x compute | 8min-30min | ~25 | Citations, Reasoning, Excerpts, Confidence | ### \### Search API | Processor | Cost (per 1K requests with 10 results) | Cost (per 1K additional results) | Best for | Latency | | --------- | -------------------------------------- | -------------------------------- | ----------------------------------------- | ------- | | Turbo | $1 | $1 | Latency-sensitive, high-volume lookups | ~200ms | | Fast | $1 | $1 | Interactive agents on a sub-second budget | ~700ms | | Basic | $5 | $1 | Longer excerpts per source in one call | ~1s | | Advanced | $5 | $1 | Multi-hop background research agents | ~3s | ### \### Extract API | Processor | Cost (per 1K results) | Best for | Latency | | --------- | --------------------- | --------------------------------- | ------------------------------ | | Extract | $1 | Direct webpage content extraction | 1s-3s (cached), 60s-90s (live) | ### \### Responses API | Processor | Cost (per 1K requests) | Best for | Latency | Basis | | --------- | ---------------------- | ------------------------------------------------------ | ------- | --------- | | Low | $10 | Simple fact-retrieval questions | ~5–10s | Citations | | Medium | $50 | Complex, multi-hop fact-retrieval | ~15–20s | Citations | | High | $250 | Deep research requiring extensive search and synthesis | ~30–60s | Citations | ### \### Monitor API | Processor | Cost (per 1K requests) | Best for | Frequency | Basis | | --------- | ---------------------- | -------------------------------------------------------- | ----------------------- | --------- | | Lite | $3 | Narrow queries — a single entity, domain, or signal type | Hourly / Daily / Weekly | Citations | | Base | $10 | Wide queries — entity classes, topic areas, regions | Hourly / Daily / Weekly | Citations | ### \### Find All API | Processor | Fixed Cost | Cost Per Match | Best for | | --------- | ---------- | -------------- | --------------------------------------------------------- | | Base | $0.25 | $0.03 | Broad, common queries where you expect many matches | | Core | $2.00 | $0.15 | Specific queries with moderate expected matches | | Pro | $10.00 | $1.00 | Highly specific queries with rare or hard-to-find matches | | Preview | $0.10 | $0.00 | Testing queries (~10 candidates) | Start building ## Scale with predictable cost Parallel APIs are priced per request, not per token. You always know the exact cost of a query before you run it. [Developer platform](https://platform.parallel.ai)[Get a demo](https://contact.parallel.ai/) ### \[Get up to $250 in free credits\] Qualified startups can receive up to $250 in free credits from Parallel [Apply now](https://form.fillout.com/t/cNxJPKmh7eus)