Agent Models | Firecrawl

Firecrawl Agent offers three models optimized for different use cases. Choose the right model based on your extraction complexity and cost requirements.

Available Models

Model	Cost	Accuracy	Best For
`spark-2`	Lowest	Comparable to Pro	Low cost and short run time
`spark-1-mini`	60% cheaper than Pro	Standard	Cost-sensitive Spark 1 workloads
`spark-1-pro`	Standard	Higher	Complex research, critical extraction (default)

Spark 1 Pro is the default, so a request without the model parameter uses spark-1-pro. Set model to spark-2 to get a lower cost and a shorter run time at comparable accuracy. Set model to spark-1-mini for a 60% lower cost on simple Spark 1 tasks.

Spark 2

spark-2 is our newest agent model. It removes the accuracy-versus-cost decision: it is cheaper and faster than both Spark 1 models while matching Spark 1 Pro’s accuracy, and it completes a higher share of runs. Set model to spark-2 to use it. Use Spark 2 when:

You want the lowest cost per run
Run time matters
You would otherwise reach for Spark 1 Pro’s accuracy

Example use cases:

Anything you run on Spark 1 Mini or Spark 1 Pro today
High-volume extraction where cost per run drives the budget
Multi-domain research that needs to come back quickly

Spark 1 Mini

spark-1-mini is our efficient model, ideal for straightforward data extraction tasks. Use Mini when:

Extracting simple data points (contact info, pricing, etc.)
Working with well-structured websites
Cost efficiency is a priority
Running high-volume extraction jobs

Example use cases:

Extracting product prices from e-commerce sites
Gathering contact information from company pages
Pulling basic metadata from articles
Simple data point lookups

Spark 1 Pro (Default)

spark-1-pro is our flagship model, designed for maximum accuracy on complex extraction tasks. It is the default: a request that does not set model uses spark-1-pro. Use Pro when:

Performing complex competitive analysis
Extracting data that requires deep reasoning
Accuracy is critical for your use case
Dealing with ambiguous or hard-to-find data

Example use cases:

Multi-domain competitive analysis
Complex research tasks requiring reasoning
Extracting nuanced information from multiple sources
Critical business intelligence gathering

Specifying a Model

spark-1-pro is the default, so the model parameter is optional. Pass it to select a different model:

from firecrawl import Firecrawl

app = Firecrawl(api_key="fc-YOUR_API_KEY")

# Using Spark 2 (not the default - set it explicitly)
result = app.agent(
    prompt="Find the pricing of Firecrawl",
    model="spark-2"
)

# Using Spark 1 Mini
result = app.agent(
    prompt="Find the pricing of Firecrawl",
    model="spark-1-mini"
)

# Using Spark 1 Pro (the default) for complex tasks
result = app.agent(
    prompt="Compare all enterprise features and pricing across Firecrawl, Apify, and ScrapingBee",
    model="spark-1-pro"
)

print(result.data)

import { Firecrawl } from 'firecrawl';

const firecrawl = new Firecrawl({ apiKey: "fc-YOUR_API_KEY" });

// Using Spark 2 (not the default - set it explicitly)
const resultSpark2 = await firecrawl.agent({
  prompt: "Find the pricing of Firecrawl",
  model: "spark-2"
});

// Using Spark 1 Mini
const result = await firecrawl.agent({
  prompt: "Find the pricing of Firecrawl",
  model: "spark-1-mini"
});

// Using Spark 1 Pro (the default) for complex tasks
const resultPro = await firecrawl.agent({
  prompt: "Compare all enterprise features and pricing across Firecrawl, Apify, and ScrapingBee",
  model: "spark-1-pro"
});

console.log(result.data);

# Using Spark 2 (not the default - set it explicitly)
curl -X POST "https://api.firecrawl.dev/v2/agent" \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Find the pricing of Firecrawl",
    "model": "spark-2"
  }'

# Using Spark 1 Mini
curl -X POST "https://api.firecrawl.dev/v2/agent" \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Find the pricing of Firecrawl",
    "model": "spark-1-mini"
  }'

# Using Spark 1 Pro (the default) for complex tasks
curl -X POST "https://api.firecrawl.dev/v2/agent" \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Compare all enterprise features and pricing across Firecrawl, Apify, and ScrapingBee",
    "model": "spark-1-pro"
  }'

Model Comparison

Feature	Spark 2	Spark 1 Mini	Spark 1 Pro
Cost	Lowest	60% cheaper than Pro	Standard
Accuracy	Comparable to Pro	Standard	Higher
Speed	Fastest	Fast	Fast
Best for	All tasks	Most tasks	Complex tasks
Reasoning	Advanced	Standard	Advanced
Multi-domain	Excellent	Good	Excellent

Pricing by Model

All models use dynamic, credit-based pricing that scales with task complexity:

Spark 2: Uses substantially fewer credits than either Spark 1 model for equivalent tasks
Spark 1 Mini: Uses approximately 60% fewer credits than Pro for equivalent tasks
Spark 1 Pro: Standard credit consumption for maximum accuracy

Credit usage varies based on prompt complexity, data processed, and output structure — regardless of model selected.

Choosing the Right Model

Spark 2 covers both branches below. The tree applies when you are choosing between the two Spark 1 models:

                    ┌─────────────────────────────────┐
                    │   What type of task?            │
                    └─────────────────────────────────┘
                                   │
                    ┌──────────────┴──────────────┐
                    ▼                             ▼
          ┌─────────────────┐           ┌─────────────────┐
          │  Simple/Direct  │           │ Complex/Research│
          │  extraction     │           │ multi-domain    │
          └─────────────────┘           └─────────────────┘
                    │                             │
                    ▼                             ▼
          ┌─────────────────┐           ┌─────────────────┐
          │  spark-1-mini   │           │  spark-1-pro    │
          │  (60% cheaper)  │           │  (higher acc.)  │
          └─────────────────┘           └─────────────────┘

API Reference

See the Agent API Reference for complete parameter documentation. Have questions about which model to use? Email help@firecrawl.com.

Are you an AI agent that needs a Firecrawl API key? See firecrawl.dev/agent-onboarding/SKILL.md for automated onboarding instructions.

Get Started

Core Endpoints

More

Quickstarts

Developer Guides

Webhooks

Use Cases

Other

Contributing

Models

Available Models

Spark 2

Spark 1 Mini

Spark 1 Pro (Default)

Specifying a Model

Model Comparison

Pricing by Model

Choosing the Right Model

API Reference

​Available Models

​Spark 2

​Spark 1 Mini

​Spark 1 Pro (Default)

​Specifying a Model

​Model Comparison

​Pricing by Model

​Choosing the Right Model

​API Reference

Available Models

Spark 2

Spark 1 Mini

Spark 1 Pro (Default)

Specifying a Model

Model Comparison

Pricing by Model

Choosing the Right Model

API Reference