Start a Firecrawl agent task
Start an agent task for agentic data extraction. Needs prompt.
Inputs
- Prompt
- The prompt describing what data to extractRequired · prompt
- URLs
- Optional list of URLs to constrain the agent toOptional · urls
- Schema
- Optional JSON schema to structure the extracted dataOptional · schema
- Max credits
- Maximum credits to spend on this agent taskOptional · maxCredits
- Strict constrain to URLs
- If true, agent will only visit URLs provided in the urls arrayOptional · strictConstrainToURLs
- Model
- The model to use for the agent task (spark-2, spark-1-mini or spark-1-pro)Optional · model
- Effort
- Reasoning budget for the agent task (low, medium or high)Optional · effort
- Webhook
- A webhook specification objectOptional · webhook
- Audit metadata
- User attribution included with SIEM logging events when SIEM Logging is enabled for the organizationOptional · auditMetadata
- Threat protection
- Per-request [Threat Protection](https://docs.firecrawl.dev/features/threat-protection) overrideOptional · threatProtection
Pricing
- Price
- $0.0025 per credit
- Billing
- The provider’s price, with no markup. Billed for measured usage.
- Price checked
- 5 October 2026
Call
Your agent reads the schema and the price with inspect_tool before it runs the tool.
- MCP call
- cURL command
- TypeScript
- Tool ID
Alternatives
- Exa answer with citationsExaUsage based
- Exa research runExaUsage based
- Firecrawl agent execution traceFirecrawlFree
- Firecrawl agent output snapshotFirecrawlFree
- Firecrawl related research papersFirecrawlUsage based
- Firecrawl research paper readerFirecrawlUsage based
- Firecrawl research paper searchFirecrawlUsage based
- Compare all 8
Connect your agent to 2,400+ tools for free
Sign in with Google or GitHub. No card required.