diff --git a/advanced-scraping-guide.mdx b/advanced-scraping-guide.mdx index e5b2c917a..a4a517b3d 100644 --- a/advanced-scraping-guide.mdx +++ b/advanced-scraping-guide.mdx @@ -464,7 +464,7 @@ Use the `/v2/agent` endpoint for autonomous, multi-page data extraction. The age | `schema` | `object` | — | JSON schema to structure the extracted data. | | `maxCredits` | `number` | `2500` | Maximum credits the agent can spend. The dashboard supports up to 2,500; for higher limits, set this via the API (values above 2,500 are always billed as paid requests). | | `strictConstrainToURLs` | `boolean` | `false` | When `true`, the agent only visits the provided URLs. | -| `model` | `string` | `"spark-1-mini"` | AI model to use. `"spark-1-mini"` (default, 60% cheaper) or `"spark-1-pro"` (higher accuracy). | +| `model` | `string` | `"spark-2"` | AI model to use. `"spark-2"` is the only model and the default. | diff --git a/api-reference/v2-openapi.json b/api-reference/v2-openapi.json index 5d0e35c76..79e24f4b2 100644 --- a/api-reference/v2-openapi.json +++ b/api-reference/v2-openapi.json @@ -2510,11 +2510,10 @@ "model": { "type": "string", "enum": [ - "spark-1-mini", - "spark-1-pro" + "spark-2" ], - "default": "spark-1-mini", - "description": "The model to use for the agent task. spark-1-mini (default) is 60% cheaper, spark-1-pro offers higher accuracy for complex tasks" + "default": "spark-2", + "description": "The model to use for the agent task. spark-2 is the default and handles every task; the retired spark-1-mini and spark-1-pro presets are also accepted and run on spark-2" }, "auditMetadata": { "$ref": "#/components/schemas/AuditMetadata" @@ -2634,12 +2633,8 @@ }, "model": { "type": "string", - "enum": [ - "spark-1-pro", - "spark-1-mini" - ], - "default": "spark-1-pro", - "description": "Model preset used for the agent run" + "default": "spark-2", + "description": "Model preset used for the agent run. New runs report spark-2; archived runs may report the retired spark-1-pro or spark-1-mini" }, "error": { "type": "string", diff --git a/developer-guides/usage-guides/choosing-the-data-extractor.mdx b/developer-guides/usage-guides/choosing-the-data-extractor.mdx index 29f69e747..66a6e9f31 100644 --- a/developer-guides/usage-guides/choosing-the-data-extractor.mdx +++ b/developer-guides/usage-guides/choosing-the-data-extractor.mdx @@ -41,7 +41,7 @@ The `/agent` endpoint is Firecrawl's most advanced offering—the successor to ` - **Autonomous Navigation**: The agent searches and navigates deep into sites to find your data - **Deep Web Search**: Autonomously discovers information across multiple domains and pages - **Parallel Processing**: Processes multiple sources simultaneously for faster results -- **Models Available**: `spark-1-mini` (default, 60% cheaper) and `spark-1-pro` (higher accuracy) +- **Model**: `spark-2` (default, and the only model) ### Example @@ -204,7 +204,7 @@ result = app.agent( urls=["https://example.com"], # Optional - can omit entirely prompt="Extract product information from example.com", schema=schema, - model="spark-1-mini" # or "spark-1-pro" for higher accuracy + model="spark-2" # default, can be omitted ) ``` diff --git a/features/agent.mdx b/features/agent.mdx index 19ccd38a9..79523c199 100644 --- a/features/agent.mdx +++ b/features/agent.mdx @@ -131,40 +131,19 @@ You can share agent runs directly from the Agent playground. Shared links are pu ## Model Selection -Firecrawl Agent offers two models. **Spark 1 Mini is 60% cheaper** and is the default — perfect for most use cases. Upgrade to Spark 1 Pro when you need maximum accuracy on complex tasks. +Firecrawl Agent runs on **Spark 2**, which handles every kind of task — from single data points to complex multi-domain research. It is faster and considerably cheaper than the Spark 1 models it replaces, at the same output quality. -| Model | Cost | Accuracy | Best For | -|-------|------|----------|----------| -| `spark-1-mini` | **60% cheaper** | Standard | Most tasks (default) | -| `spark-1-pro` | Standard | Higher | Complex research, critical extraction | +| Model | Best For | +|-------|----------| +| `spark-2` | All agent tasks (default) | - -**Start with Spark 1 Mini** (default) — it handles most extraction tasks well at 60% lower cost. Switch to Pro only for complex multi-domain research or when accuracy is critical. - - -### Spark 1 Mini (Default) - -`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 - -### Spark 1 Pro - -`spark-1-pro` is our flagship model, designed for maximum accuracy on complex extraction tasks. - -**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 + +`spark-1-mini` and `spark-1-pro` are retired. Requests that still pass them run on `spark-2`. + ### Specifying a Model -Pass the `model` parameter to select which model to use: +`spark-2` is the default, so the `model` parameter is optional: @@ -179,7 +158,7 @@ Pass the `model` parameter to select which model to use: | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `prompt` | string | **Yes** | Natural language description of the data you want to extract (max 10,000 characters) | -| `model` | string | No | Model to use: `spark-1-mini` (default) or `spark-1-pro` | +| `model` | string | No | Model to use: `spark-2` (default) | | `urls` | array | No | Optional list of URLs to focus the extraction | | `schema` | object | No | Optional JSON schema for structured output | | `maxCredits` | number | No | Maximum number of credits to spend on this agent task. Defaults to **2,500** if not set. The dashboard supports values up to **2,500**; for higher limits, set `maxCredits` via the API (values above 2,500 are always treated as paid requests). If the limit is reached, the job fails and **no data is returned**. Failed runs are not billed: credits used for AI reasoning are never charged on failure, any credits used for tool calls during the run (scraping, search, mapping, etc.) are refunded, and the response reports `creditsUsed: 0`. | diff --git a/features/models.mdx b/features/models.mdx index bb4a580c9..cacd979ae 100644 --- a/features/models.mdx +++ b/features/models.mdx @@ -1,8 +1,8 @@ --- title: "Models" -description: "Choose the right model for your agent extraction tasks." +description: "The model behind Firecrawl Agent." og:title: "Agent Models | Firecrawl" -og:description: "Choose between Spark 1 Mini and Spark 1 Pro for your agent extraction tasks." +og:description: "Spark 2 powers Firecrawl Agent: faster, cheaper, and available on every agent task." sidebarTitle: "Models" hidden: true noindex: true @@ -13,54 +13,27 @@ import AgentWithModelPython from "/snippets/v2/agent/with-model/python.mdx"; import AgentWithModelJS from "/snippets/v2/agent/with-model/js.mdx"; import AgentWithModelCURL from "/snippets/v2/agent/with-model/curl.mdx"; -Firecrawl Agent offers two models optimized for different use cases. Choose the right model based on your extraction complexity and cost requirements. +Firecrawl Agent runs on a single model, **Spark 2**. There is nothing to tune: the same model handles simple lookups and deep multi-domain research. ## Available Models -| Model | Cost | Accuracy | Best For | -|-------|------|----------|----------| -| `spark-1-mini` | **60% cheaper** | Standard | Most tasks (default) | -| `spark-1-pro` | Standard | Higher | Complex research, critical extraction | +| Model | Best For | +|-------|----------| +| `spark-2` | All agent tasks (default) | - -**Start with Spark 1 Mini** (default) — it handles most extraction tasks well at 60% lower cost. Switch to Pro only for complex multi-domain research or when accuracy is critical. - +Spark 2 replaces `spark-1-mini` and `spark-1-pro`. Compared to Spark 1 it is: -## Spark 1 Mini (Default) +- **Cheaper** — most runs cost a fraction of what the same task cost on Spark 1 +- **Faster** — it finishes in a small fraction of the time at the median, and its slowest runs are far shorter +- **At least as accurate** — output quality matches `spark-1-pro`, and more runs finish successfully -`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 - -`spark-1-pro` is our flagship model, designed for maximum accuracy on complex extraction tasks. - -**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 + +`spark-1-mini` and `spark-1-pro` are retired. Requests that still pass them run on `spark-2`, so no code change is required. + ## Specifying a Model -Pass the `model` parameter to select which model to use: +`spark-2` is the default, so the `model` parameter is optional: @@ -70,53 +43,18 @@ Pass the `model` parameter to select which model to use: -## Model Comparison - -| Feature | Spark 1 Mini | Spark 1 Pro | -|---------|--------------|-------------| -| **Cost** | 60% cheaper | Standard | -| **Accuracy** | Standard | Higher | -| **Speed** | Fast | Fast | -| **Best for** | Most tasks | Complex tasks | -| **Reasoning** | Standard | Advanced | -| **Multi-domain** | Good | Excellent | +## Pricing -## Pricing by Model - -Both models use dynamic, credit-based pricing that scales with task complexity: - -- **Spark 1 Mini**: Uses approximately 60% fewer credits than Pro for equivalent tasks -- **Spark 1 Pro**: Standard credit consumption for maximum accuracy +Spark 2 uses dynamic, credit-based pricing that scales with task complexity. -Credit usage varies based on prompt complexity, data processed, and output structure — regardless of model selected. +Credit usage varies based on prompt complexity, data processed, and output structure. -## Choosing the Right Model - -``` - ┌─────────────────────────────────┐ - │ 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](/api-reference/endpoint/agent) for complete parameter documentation. -Have questions about which model to use? Email [help@firecrawl.com](mailto:help@firecrawl.com). +Have questions? Email [help@firecrawl.com](mailto:help@firecrawl.com). > Are you an AI agent that needs a Firecrawl API key? See [firecrawl.dev/agent-onboarding/SKILL.md](https://www.firecrawl.dev/agent-onboarding/SKILL.md) for automated onboarding instructions. diff --git a/sdks/cli.mdx b/sdks/cli.mdx index 82ea2cbaf..6838b796b 100644 --- a/sdks/cli.mdx +++ b/sdks/cli.mdx @@ -356,7 +356,7 @@ Search and gather data from the web using natural language prompts. | Option | Description | | --------------------------- | -------------------------------------------------------------------------------------- | | `--urls ` | Optional list of URLs to focus the agent on (comma-separated) | -| `--model ` | Model to use: `spark-1-mini` (default, 60% cheaper) or `spark-1-pro` (higher accuracy) | +| `--model ` | Model to use: `spark-2` (default) | | `--schema ` | JSON schema for structured output (inline JSON string) | | `--schema-file ` | Path to JSON schema file for structured output | | `--max-credits ` | Maximum credits to spend (job fails if limit reached) | diff --git a/snippets/v2/agent/base/curl.mdx b/snippets/v2/agent/base/curl.mdx index 643be1c46..ac072ca57 100644 --- a/snippets/v2/agent/base/curl.mdx +++ b/snippets/v2/agent/base/curl.mdx @@ -4,7 +4,7 @@ curl -X POST "https://api.firecrawl.dev/v2/agent" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Extract the main features and benefits of Firecrawl", - "model": "spark-1-mini" + "model": "spark-2" }' ``` diff --git a/snippets/v2/agent/base/js.mdx b/snippets/v2/agent/base/js.mdx index 4f1f571b4..7f28a27b5 100644 --- a/snippets/v2/agent/base/js.mdx +++ b/snippets/v2/agent/base/js.mdx @@ -5,7 +5,7 @@ const firecrawl = new Firecrawl({ apiKey: "fc-YOUR_API_KEY" }); const result = await firecrawl.agent({ prompt: "Extract the main features and benefits of Firecrawl", - model: "spark-1-mini" + model: "spark-2" }); console.log(result.data); diff --git a/snippets/v2/agent/base/python.mdx b/snippets/v2/agent/base/python.mdx index d12a27741..4392f8f8d 100644 --- a/snippets/v2/agent/base/python.mdx +++ b/snippets/v2/agent/base/python.mdx @@ -5,7 +5,7 @@ app = Firecrawl(api_key="fc-YOUR_API_KEY") result = app.agent( prompt="Extract the main features and benefits of Firecrawl", - model="spark-1-mini" + model="spark-2" ) print(result.data) diff --git a/snippets/v2/agent/with-model/curl.mdx b/snippets/v2/agent/with-model/curl.mdx index caed185e9..6f88d0389 100644 --- a/snippets/v2/agent/with-model/curl.mdx +++ b/snippets/v2/agent/with-model/curl.mdx @@ -1,21 +1,10 @@ ```bash cURL -# Using Spark 1 Mini (default) +# spark-2 is the default, so model can be omitted 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 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": "spark-2" }' ``` - - diff --git a/snippets/v2/agent/with-model/js.mdx b/snippets/v2/agent/with-model/js.mdx index 4dc2406d3..af3550530 100644 --- a/snippets/v2/agent/with-model/js.mdx +++ b/snippets/v2/agent/with-model/js.mdx @@ -3,19 +3,11 @@ import { Firecrawl } from 'firecrawl'; const firecrawl = new Firecrawl({ apiKey: "fc-YOUR_API_KEY" }); -// Using Spark 1 Mini (default - can be omitted) +// spark-2 is the default, so model can be omitted const result = await firecrawl.agent({ prompt: "Find the pricing of Firecrawl", - model: "spark-1-mini" -}); - -// Using Spark 1 Pro for complex tasks -const resultPro = await firecrawl.agent({ - prompt: "Compare all enterprise features and pricing across Firecrawl, Apify, and ScrapingBee", - model: "spark-1-pro" + model: "spark-2" }); console.log(result.data); ``` - - diff --git a/snippets/v2/agent/with-model/python.mdx b/snippets/v2/agent/with-model/python.mdx index 70963f656..6f2493c7c 100644 --- a/snippets/v2/agent/with-model/python.mdx +++ b/snippets/v2/agent/with-model/python.mdx @@ -3,19 +3,11 @@ from firecrawl import Firecrawl app = Firecrawl(api_key="fc-YOUR_API_KEY") -# Using Spark 1 Mini (default - can be omitted) +# spark-2 is the default, so model can be omitted result = app.agent( prompt="Find the pricing of Firecrawl", - model="spark-1-mini" -) - -# Using Spark 1 Pro for complex tasks -result = app.agent( - prompt="Compare all enterprise features and pricing across Firecrawl, Apify, and ScrapingBee", - model="spark-1-pro" + model="spark-2" ) print(result.data) ``` - - diff --git a/snippets/v2/cli/agent/options.mdx b/snippets/v2/cli/agent/options.mdx index f432a673a..3dcb2460a 100644 --- a/snippets/v2/cli/agent/options.mdx +++ b/snippets/v2/cli/agent/options.mdx @@ -1,6 +1,6 @@ ```bash CLI -# Use Spark 1 Pro for higher accuracy -firecrawl agent "Competitive analysis across multiple domains" --model spark-1-pro --wait +# Explicitly select the model (spark-2 is the default) +firecrawl agent "Competitive analysis across multiple domains" --model spark-2 --wait # Set max credits to limit costs firecrawl agent "Gather contact information from company websites" --max-credits 100 --wait