--- type: "firecrawl-provider" description: "Vercel (vercel.com) read through the Markdown twins the site publishes for agents: docs search over the semantic docs sitemap, the REST API endpoint index, the AI Gateway model catalog with per-model pages and token prices, Marketplace integrations, any docs page, knowledge base guide, blog post, changelog entry or template page as clean Markdown with an outline and section reads, the changelog newest first, the blog index, the template gallery by framework and use case, and plan pricing with included usage and overage prices as structured data. Public pages only; no login or key." use_when: "Vercel (vercel.com) read through the Markdown twins the site publishes for agents: docs search over the semantic docs sitemap, the REST API endpoint index, the AI Gateway model catalog with per-model pages and token prices, Marketplace integrations, any docs page, knowledge base guide, blog post, changelog entry or template page as clean Markdown with an outline and section reads, the changelog newest first, the blog index, the template gallery by framework and use case, and plan pricing with included usage and overage prices as structured data. Public pages only; no login or key." categories: "Developer" capabilities: 10 credits_per_call: 5 --- # Vercel on Firecrawl Alexandria Vercel (vercel.com) read through the Markdown twins the site publishes for agents: docs search over the semantic docs sitemap, the REST API endpoint index, the AI Gateway model catalog with per-model pages and token prices, Marketplace integrations, any docs page, knowledge base guide, blog post, changelog entry or template page as clean Markdown with an outline and section reads, the changelog newest first, the blog index, the template gallery by framework and use case, and plan pricing with included usage and overage prices as structured data. Public pages only; no login or key. - Categories: Developer - Category index: [Developer category](https://firecrawl.dev/alexandria/agents/categories/developer) - Provider key: `vercel-com` - Access: Firecrawl credits - Cost: 5 credits per call ## More - [Human guide](https://firecrawl.dev/app/alexandria/vercel-com) - [OpenAPI spec](https://firecrawl.dev/alexandria/agents/providers/vercel-com/openapi.json) ## Capabilities - [Changelog](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/changelog): Vercel changelog entries newest first from the changelog sitemap (GET /changelog/sitemap.md, every entry since 2020 with its date), each with date, title, slug, URL and, for entries on the three newest feed pages (/changelog.md, /changelog/page/{n}.md), the one-line summary. `q` matches title words, `since`/`until` bound the date. Paginates with `offset`. - [Get ai gateway model](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/get_ai_gateway_model): One AI Gateway model page (GET /ai-gateway/models/{slug}.md): id, name, type, serving providers, context window, maximum output tokens, input and output prices per million tokens, description, outline and the page Markdown (supported parameters, example, guidance). Accepts a model id (`openai/gpt-4o`), a bare slug or a model page URL. A full id must match the page's Model ID; unknown models are `not_found`. - [Get page](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/get_page): One vercel.com page as clean Markdown from its public Markdown twin (GET /{path}.md): docs pages, knowledge base guides, blog posts, customer stories, changelog entries and template pages. Returns title, description, dates, authors, category, template links, an outline of headings with anchors, and the content; `section` (heading text or anchor) returns only that heading and its subsections; `max_chars` cuts content. Accepts a path (`functions` means `docs/functions`) or a pasted vercel.com URL, whose anchor selects the section. REST API reference pages also return their method and path; `include_tables` returns limits, pricing and parameter tables as structured rows. Unknown pages and sections are `not_found`. - [Get pricing](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/get_pricing): Vercel plan pricing from the pricing page's Markdown twin (GET /pricing.md): the plans (Hobby, Pro, Enterprise) with price and audience, and every pricing row (group, section, feature, docs link, description) with each plan's cell split into included allowance and usage price, plus the pricing FAQs. `group` and `q` narrow the rows. - [List ai gateway models](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_ai_gateway_models): Every model in the Vercel AI Gateway catalog (GET /ai-gateway/models.md, about 400 models) with id, creator, type, context window, input, output and cached-input prices per million tokens, serving providers, capability tags, zero data retention, description and detail URL. `provider` matches the creator or any serving provider; `type`, `capability` and `q` narrow it. Paginates with `offset`. - [List blog posts](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_blog_posts): Vercel blog posts newest first from the blog index (GET /blog.md, every post and customer story with publication date, category and summary). `q` matches title, slug and summary words, `category` (Engineering, Company News, Customers, ...) and `since`/`until` narrow it. Paginates with `offset`. - [List marketplace integrations](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_marketplace_integrations): Integrations listed on the Vercel Marketplace page (GET /marketplace.md): section (native Marketplace integrations or external integrations), name, slug, URL, description and products. `q` matches name, description and product words; `section` narrows it. Paginates with `offset`. - [List rest api endpoints](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_rest_api_endpoints): The Vercel REST API endpoint index from the reference page (GET /docs/rest-api.md, about 450 endpoints): group, HTTP method, path, summary and the docs page for each. `q` matches method, path, summary and group words; `group` and `method` narrow it. Paginates with `offset`. - [List templates](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_templates): Templates from the Vercel template gallery (GET /templates.md, or /templates/{filter}.md for one filter) with title, framework, slug, URL and description. `framework` and `use_case` take gallery filter slugs (`next.js`, `nuxt`, `svelte`, `astro`, `ai`, `starter`, `ecommerce`, `blog`, ...); both together return templates in both lists. `q` matches title and description words. Unknown filter slugs are invalid input. Paginates with `offset`. - [Search docs](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/search_docs): Search or list Vercel documentation pages from the docs semantic sitemap (GET /docs/sitemap.md, about 1,700 pages with type, last-modified date, summary, prerequisites and topics). `q` keyword-ranks pages by title, path, topics and summary (every word must match); without `q` the pages come in docs-tree order. `group` and `page_type` narrow the list. Paginates with `offset`. ## 1. Choose this provider when Vercel (vercel.com) read through the Markdown twins the site publishes for agents: docs search over the semantic docs sitemap, the REST API endpoint index, the AI Gateway model catalog with per-model pages and token prices, Marketplace integrations, any docs page, knowledge base guide, blog post, changelog entry or template page as clean Markdown with an outline and section reads, the changelog newest first, the blog index, the template gallery by framework and use case, and plan pricing with included usage and overage prices as structured data. Public pages only; no login or key. ## 2. Minimal request Call `POST https://api.firecrawl.dev/v2/scrape` with `{ alexandria: { provider, capability, options } }`. For a batch, send `{ alexandria: [...] }` with up to 10 calls. ```json { "provider": "vercel-com", "capability": "developer-documentation/changelog", "options": { "limit": 5 } } ``` ## 3. Add provider options Use only the options needed for the task: - `limit` (number): Results per call, 1 to 100. Defaults to 10. Example: `10` - `offset` (number): Skip this many matches; pass the previous `next_offset` (also the continuation). Example: `10` - `q` (string): Words that must all appear in the title, e.g. `ai gateway`. Example: `ai gateway` - `since` (string): Only entries on or after this date (YYYY-MM-DD). Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` - `until` (string): Only entries on or before this date (YYYY-MM-DD). Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` ## 4. Request through your preferred interface ### JavaScript ```javascript const result = await firecrawl.scrape({ alexandria: { provider: "vercel-com", capability: "developer-documentation/changelog", options: { limit: 5, }, }, }); ``` ### Python ```python result = firecrawl.scrape_alexandria({ "provider": "vercel-com", "capability": "developer-documentation/changelog", "options": { "limit": 5 } }) ``` ### cURL ```sh curl https://api.firecrawl.dev/v2/scrape \ -H "Authorization: Bearer $FIRECRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "alexandria": { "provider": "vercel-com", "capability": "developer-documentation/changelog", "options": { "limit": 5 } } }' ``` ### CLI ```sh firecrawl scrape 'vercel-com/developer-documentation/changelog' \ --options '{"limit":5}' ``` ### MCP Call the FCX MCP retrieve tool with this object: ```json { "provider": "vercel-com", "capability": "developer-documentation/changelog", "options": { "limit": 5 } } ``` Ask for only the returned fields needed by the task. ## 5. Full request shape ```json { "provider": "vercel-com", "capability": "developer-documentation/changelog", "options": { "limit": 5 } } ``` ## 6. Response data The response includes `success`, `provider`, `capability`, `creditsCost` and `data`. This example shows the provider payload in `data`: ```json { "count": 5, "entries": [ { "date": "2026-10-22", "markdown_url": "https://vercel.com/changelog/eight-more-tlds-now-eligible-for-a-free-domain-with-pro.md", "slug": "eight-more-tlds-now-eligible-for-a-free-domain-with-pro", "summary": "The free domain offer for Pro teams now covers eight more TLDs, including .co, .studio, and .agency, for sixteen in total.", "title": "Eight more TLDs now eligible for a free domain with Pro", "url": "https://vercel.com/changelog/eight-more-tlds-now-eligible-for-a-free-domain-with-pro" }, { "date": "2026-10-21", "markdown_url": "https://vercel.com/changelog/routing-middleware-now-supports-python.md", "slug": "routing-middleware-now-supports-python", "summary": "You can now write routing middleware in Python with the vercel-proxy package, and configure them with the proxy property in vercel.json.", "title": "Routing Middleware now supports Python", "url": "https://vercel.com/changelog/routing-middleware-now-supports-python" }, { "date": "2026-10-21", "markdown_url": "https://vercel.com/changelog/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free.md", "slug": "basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free", "summary": "Use Baseten's Mammoth-1 and Elephant-1 free through October 27 on Vercel AI Gateway, with one API key, usage tracking, and shared budgets.", "title": "Baseten's Mammoth-1 and Elephant-1 now available on AI Gateway for free", "url": "https://vercel.com/changelog/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free" }, { "date": "2026-10-21", "markdown_url": "https://vercel.com/changelog/skipped-monorepo-deployments-no-longer-count-against-limits.md", "slug": "skipped-monorepo-deployments-no-longer-count-against-limits", "summary": "Deployments that Vercel automatically skips in a monorepo no longer count against your deployment rate limits, giving teams more real deployments from the same limits.", "title": "Skipped monorepo deployments no longer count against limits", "url": "https://vercel.com/changelog/skipped-monorepo-deployments-no-longer-count-against-limits" }, { "date": "2026-10-20", "markdown_url": "https://vercel.com/changelog/websocket-support-is-now-generally-available.md", "slug": "websocket-support-is-now-generally-available", "summary": "WebSocket support in Vercel Functions, used for multiplayer apps, chat streaming, and AI Gateway's realtime models, is now GA.", "title": "WebSocket support is now generally available", "url": "https://vercel.com/changelog/websocket-support-is-now-generally-available" } ], "listed_count": 1440, "next_offset": 5, "observed_at_ms": 1792700000000, "query": { "limit": 5, "offset": 0, "q": null, "since": null, "until": null }, "source_url": "https://vercel.com/changelog/sitemap.md", "total_count": 1440 } ``` ## API reference-derived contract The following capability contract is generated from the same normalized Alexandria API reference exposed in the API spec. ### Changelog - Capability: `developer-documentation/changelog` - Description: Vercel changelog entries newest first from the changelog sitemap (GET /changelog/sitemap.md, every entry since 2020 with its date), each with date, title, slug, URL and, for entries on the three newest feed pages (/changelog.md, /changelog/page/{n}.md), the one-line summary. `q` matches title words, `since`/`until` bound the date. Paginates with `offset`. - Instructions: To see what Vercel shipped recently or find when a feature launched; read a full entry with `get_page` using `changelog/`. - Cost: 5 credits per call - Capability file: [Changelog](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/changelog) Accepted options: - `limit` (number): Results per call, 1 to 100. Defaults to 10. Example: `10` - `offset` (number): Skip this many matches; pass the previous `next_offset` (also the continuation). Example: `10` - `q` (string): Words that must all appear in the title, e.g. `ai gateway`. Example: `ai gateway` - `since` (string): Only entries on or after this date (YYYY-MM-DD). Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` - `until` (string): Only entries on or before this date (YYYY-MM-DD). Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` Response schema example: ```json { "count": 5, "entries": [ { "date": "2026-10-22", "markdown_url": "https://vercel.com/changelog/eight-more-tlds-now-eligible-for-a-free-domain-with-pro.md", "slug": "eight-more-tlds-now-eligible-for-a-free-domain-with-pro", "summary": "The free domain offer for Pro teams now covers eight more TLDs, including .co, .studio, and .agency, for sixteen in total.", "title": "Eight more TLDs now eligible for a free domain with Pro", "url": "https://vercel.com/changelog/eight-more-tlds-now-eligible-for-a-free-domain-with-pro" }, { "date": "2026-10-21", "markdown_url": "https://vercel.com/changelog/routing-middleware-now-supports-python.md", "slug": "routing-middleware-now-supports-python", "summary": "You can now write routing middleware in Python with the vercel-proxy package, and configure them with the proxy property in vercel.json.", "title": "Routing Middleware now supports Python", "url": "https://vercel.com/changelog/routing-middleware-now-supports-python" }, { "date": "2026-10-21", "markdown_url": "https://vercel.com/changelog/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free.md", "slug": "basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free", "summary": "Use Baseten's Mammoth-1 and Elephant-1 free through October 27 on Vercel AI Gateway, with one API key, usage tracking, and shared budgets.", "title": "Baseten's Mammoth-1 and Elephant-1 now available on AI Gateway for free", "url": "https://vercel.com/changelog/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free" }, { "date": "2026-10-21", "markdown_url": "https://vercel.com/changelog/skipped-monorepo-deployments-no-longer-count-against-limits.md", "slug": "skipped-monorepo-deployments-no-longer-count-against-limits", "summary": "Deployments that Vercel automatically skips in a monorepo no longer count against your deployment rate limits, giving teams more real deployments from the same limits.", "title": "Skipped monorepo deployments no longer count against limits", "url": "https://vercel.com/changelog/skipped-monorepo-deployments-no-longer-count-against-limits" }, { "date": "2026-10-20", "markdown_url": "https://vercel.com/changelog/websocket-support-is-now-generally-available.md", "slug": "websocket-support-is-now-generally-available", "summary": "WebSocket support in Vercel Functions, used for multiplayer apps, chat streaming, and AI Gateway's realtime models, is now GA.", "title": "WebSocket support is now generally available", "url": "https://vercel.com/changelog/websocket-support-is-now-generally-available" } ], "listed_count": 1440, "next_offset": 5, "observed_at_ms": 1792700000000, "query": { "limit": 5, "offset": 0, "q": null, "since": null, "until": null }, "source_url": "https://vercel.com/changelog/sitemap.md", "total_count": 1440 } ``` ### Get ai gateway model - Capability: `developer-documentation/get_ai_gateway_model` - Description: One AI Gateway model page (GET /ai-gateway/models/{slug}.md): id, name, type, serving providers, context window, maximum output tokens, input and output prices per million tokens, description, outline and the page Markdown (supported parameters, example, guidance). Accepts a model id (`openai/gpt-4o`), a bare slug or a model page URL. A full id must match the page's Model ID; unknown models are `not_found`. - Instructions: To read details, pricing and usage guidance for a specific AI Gateway model. - Cost: 5 credits per call - Capability file: [Get ai gateway model](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/get_ai_gateway_model) Accepted options: - `max_chars` (number): Cut `content` to this many characters. Example: `200` - `model` (string): Model id like `openai/gpt-4o`, or the page slug like `gpt-4o`. Example: `openai/gpt-4o` - `url` (string): Alternatively a page URL like https://vercel.com/ai-gateway/models/gpt-4o. Pattern: ^https?://. Example: `` Response schema example: ```json { "chars": 6066, "content": "# GPT-4o\n\nThe \"omni\" model that unified text, audio, and vision in a single natively multimodal architecture, with audio response speeds averaging 320ms, a 16x improvement over prior voice pipeline approaches.\n\n- **Model ID:** `openai/gpt-4o`\n- **Type:** chat\n- **Providers:** azure, openai\n- **Context window:** 128,000\n- **Maximum output tokens:** 16,384\n- **Pricing:** $2.5/1M input tokens, $10.0/1M output tokens\n- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-4o\n\n## Supported parameters\n\nDetailed capability metadata has not been reported for this model.\n\n## Example\n\n```ts\nimport { streamText } from 'ai'\n\nconst result = streamText({\n model: 'openai/gpt-4o',\n prompt: 'Why is the sky blue?'\n})\n```\n\n## About\n\nGPT-4o was announced on May 13, 2024 at OpenAI's Spring Updates eve", "context_window": 128000, "creator": "openai", "description": "The \"omni\" model that unified text, audio, and vision in a single natively multimodal architecture, with audio response speeds averaging 320ms, a 16x improvement over prior voice pipeline approaches.", "id": "openai/gpt-4o", "input_price_per_million": 2.5, "markdown_url": "https://vercel.com/ai-gateway/models/gpt-4o.md", "max_output_tokens": 16384, "name": "GPT-4o", "observed_at_ms": 1792700000000, "outline": [ { "anchor": "supported-parameters", "level": 2, "text": "Supported parameters" }, { "anchor": "example", "level": 2, "text": "Example" }, { "anchor": "about", "level": 2, "text": "About" }, { "anchor": "what-to-consider", "level": 2, "text": "What to consider" }, { "anchor": "when-to-use", "level": 2, "text": "When to use" }, { "anchor": "best-for", "level": 3, "text": "Best For" }, { "anchor": "consider-alternatives-when", "level": 3, "text": "Consider Alternatives When" }, { "anchor": "best-for", "level": 2, "text": "Best for" }, { "anchor": "consider-alternatives", "level": 2, "text": "Consider alternatives" }, { "anchor": "frequently-asked-questions", "level": 2, "text": "Frequently asked questions" }, { "anchor": "what-does-omni-mean-in-gpt-4os-name", "level": 3, "text": "What does \"omni\" mean in GPT-4o's name?" }, { "anchor": "how-much-faster-is-gpt-4os-audio-response-compared-to-earlier-voice-pipelines", "level": 3, "text": "How much faster is GPT-4o's audio response compared to earlier voice pipelines?" }, { "anchor": "how-does-gpt-4os-api-pricing-compare-to-gpt-4-turbo", "level": 3, "text": "How does GPT-4o's API pricing compare to GPT-4 Turbo?" }, { "anchor": "what-input-and-output-modalities-does-gpt-4o-support", "level": 3, "text": "What input and output modalities does GPT-4o support?" }, { "anchor": "is-the-gpt-4o-model-alias-the-same-as-a-specific-dated-snapshot", "level": 3, "text": "Is the \"gpt-4o\" model alias the same as a specific dated snapshot?" }, { "anchor": "does-routing-gpt-4o-through-ai-gateway-add-latency", "level": 3, "text": "Does routing GPT-4o through AI Gateway add latency?" }, { "anchor": "what-are-typical-latency-characteristics", "level": 3, "text": "What are typical latency characteristics?" }, { "anchor": "links", "level": 2, "text": "Links" } ], "output_price_per_million": 10, "pricing_text": "$2.5/1M input tokens, $10.0/1M output tokens", "providers": [ "azure", "openai" ], "truncated": true, "type": "chat", "url": "https://vercel.com/ai-gateway/models/gpt-4o" } ``` ### Get page - Capability: `developer-documentation/get_page` - Description: One vercel.com page as clean Markdown from its public Markdown twin (GET /{path}.md): docs pages, knowledge base guides, blog posts, customer stories, changelog entries and template pages. Returns title, description, dates, authors, category, template links, an outline of headings with anchors, and the content; `section` (heading text or anchor) returns only that heading and its subsections; `max_chars` cuts content. Accepts a path (`functions` means `docs/functions`) or a pasted vercel.com URL, whose anchor selects the section. REST API reference pages also return their method and path; `include_tables` returns limits, pricing and parameter tables as structured rows. Unknown pages and sections are `not_found`. - Instructions: To read Vercel documentation, a KB guide, a blog post, a changelog entry or a template's README. Call without `section` and with a small `max_chars` to see the outline, then fetch the section you need. For limits and pricing pages (docs/limits, docs/plans, docs/pricing, docs/analytics/limits-and-pricing) set `include_tables`. - Cost: 5 credits per call - Capability file: [Get page](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/get_page) Accepted options: - `include_tables` (boolean): Also return every Markdown table in the returned scope as structured rows (`tables`). Defaults to false. Example: `false` - `max_chars` (number): Cut `content` to this many characters. The whole page or section is returned when omitted. Example: `200` - `path` (string): Page path such as `functions`, `docs/functions/streaming-functions`, `kb/guide/`, `blog/`, `changelog/` or `templates/next.js/`. `.md` and a `#anchor` are accepted. Example: `` - `section` (string): Heading text or anchor of the section to return, e.g. `Handle a request` or `handle-a-request`. Example: `Handle a request` - `url` (string): Alternatively a vercel.com page URL, e.g. https://vercel.com/docs/functions#handle-a-request. Pattern: ^https?://. Example: `` Response schema example: ```json { "authors": [], "category": null, "chars": 897, "content": "## Vercel Functions\n\nVercel Functions run on [Fluid compute](/docs/fluid-compute), which is enabled by default for new projects. Its key limits per plan:\n\n| Limit | Hobby | Pro and Enterprise |\n| ----------------------------------------------------------------- | -------------------------------- | -------------------------------------------------------- |\n| [Maximum duration](/docs/functions/limitations#max-duration) | 300s (5 minutes) default and max | 300s default, 800s max, up to 1800s (30 minutes) in beta |\n| [Memory and CPU](/docs/functions/limitations#memory-size-limits) | 2 GB / 1 vCPU default and max | 2 GB / 1 vCPU default, up to 4 GB / 2 vCPU max |\n\nFor the full reference, see [Vercel Functions limitations](/docs/functions/limitations).", "description": "Look up account limits, usage summaries, rate limits, and resource constraints for every Vercel plan.", "endpoint": null, "kind": "docs", "last_updated": "2026-09-16", "links": null, "markdown_url": "https://vercel.com/docs/limits.md", "observed_at_ms": 1792700000000, "outline": [ { "anchor": "vercel-functions", "level": 2, "text": "Vercel Functions" } ], "page_type": "reference", "path": "docs/limits", "published": null, "section": { "anchor": "vercel-functions", "level": 2, "text": "Vercel Functions", "url": "https://vercel.com/docs/limits#vercel-functions" }, "tables": [ { "columns": [ "Limit", "Hobby", "Pro and Enterprise" ], "heading": "Vercel Functions", "rows": [ [ "Maximum duration", "300s (5 minutes) default and max", "300s default, 800s max, up to 1800s (30 minutes) in beta" ], [ "Memory and CPU", "2 GB / 1 vCPU default and max", "2 GB / 1 vCPU default, up to 4 GB / 2 vCPU max" ] ] } ], "title": "Limits", "truncated": false, "url": "https://vercel.com/docs/limits" } ``` ### Get pricing - Capability: `developer-documentation/get_pricing` - Description: Vercel plan pricing from the pricing page's Markdown twin (GET /pricing.md): the plans (Hobby, Pro, Enterprise) with price and audience, and every pricing row (group, section, feature, docs link, description) with each plan's cell split into included allowance and usage price, plus the pricing FAQs. `group` and `q` narrow the rows. - Instructions: To answer what a Vercel plan costs, what usage is included (CDN requests, data transfer, function CPU, ISR, Blob, Sandbox, builds) and the overage price. - Cost: 5 credits per call - Capability file: [Get pricing](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/get_pricing) Accepted options: - `group` (string): Pricing group name or part of it, e.g. `Compute`, `Delivery Network`, `Observability`. Example: `` - `include_faqs` (boolean): Include the pricing FAQs. Defaults to true. Example: `false` - `q` (string): Words that must all appear in the row's group, section, feature or description, e.g. `active cpu`. Example: `active cpu` Response schema example: ```json { "count": 22, "faqs": [], "groups": [ "Vercel Compute" ], "items": [ { "description": "Time your code is actively executing in an instance.", "docs_url": null, "feature": "Fluid Active CPU", "group": "Vercel Compute", "section": "Vercel Functions", "values": [ { "included": "4 hours / month included", "plan": "Hobby", "price": null, "text": "4 hours / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.128 per hour", "text": "Starting at $0.128 per hour" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Memory allocated to a Vercel Function instance, which can include many function invocations in one.", "docs_url": null, "feature": "Fluid Provisioned Memory", "group": "Vercel Compute", "section": "Vercel Functions", "values": [ { "included": "360 GB-hrs / month included", "plan": "Hobby", "price": null, "text": "360 GB-hrs / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.0106 per GB-hr", "text": "Starting at $0.0106 per GB-hr" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "The number of times you call Vercel Functions.", "docs_url": null, "feature": "Function Invocations", "group": "Vercel Compute", "section": "Vercel Functions", "values": [ { "included": "1M / month included", "plan": "Hobby", "price": null, "text": "1M / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.60 per 1M", "text": "Starting at $0.60 per 1M" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Deploy multiple backends and frontends within a single Vercel project. Includes calls from one service to another over a binding.", "docs_url": null, "feature": "Service Requests (Beta)", "group": "Vercel Compute", "section": "Service Requests (Beta)", "values": [ { "included": "1M requests / month included", "plan": "Hobby", "price": null, "text": "1M requests / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.50 per 1M", "text": "Starting at $0.50 per 1M" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Time your code is actively executing in an instance.", "docs_url": null, "feature": "Sandbox Active CPU", "group": "Vercel Compute", "section": "Vercel Sandbox", "values": [ { "included": "5 hours / month included", "plan": "Hobby", "price": null, "text": "5 hours / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.128 per hour", "text": "Starting at $0.128 per hour" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Memory allocated to a Vercel Sandbox.", "docs_url": null, "feature": "Sandbox Provisioned Memory", "group": "Vercel Compute", "section": "Vercel Sandbox", "values": [ { "included": "420 GB-hrs / month included", "plan": "Hobby", "price": null, "text": "420 GB-hrs / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.0212 per GB-hr", "text": "Starting at $0.0212 per GB-hr" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "The number of times you started a sandbox.", "docs_url": null, "feature": "Sandbox Creations", "group": "Vercel Compute", "section": "Vercel Sandbox", "values": [ { "included": "5K / month included", "plan": "Hobby", "price": null, "text": "5K / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.60 per 1,000,000 creations", "text": "Starting at $0.60 per 1,000,000 creations" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Data your sandbox sends to the internet, plus all traffic to and from exposed ports, is billable. Data your sandbox downloads from the internet is free.", "docs_url": null, "feature": "Sandbox Data Transfer", "group": "Vercel Compute", "section": "Vercel Sandbox", "values": [ { "included": "20 GB / month included", "plan": "Hobby", "price": null, "text": "20 GB / month included" }, { "included": null, "plan": "Pro", "price": null, "text": "Included in Flat Rate CDN" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": null, "docs_url": null, "feature": "Concurrent Sandboxes", "group": "Vercel Compute", "section": "Vercel Sandbox", "values": [ { "included": null, "plan": "Hobby", "price": null, "text": "10" }, { "included": null, "plan": "Pro", "price": null, "text": "10K" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "The total amount of storage used for storing Sandbox Snapshots.", "docs_url": null, "feature": "Snapshot Storage", "group": "Vercel Compute", "section": "Vercel Sandbox", "values": [ { "included": null, "plan": "Hobby", "price": null, "text": "15 GB" }, { "included": null, "plan": "Pro", "price": "Starting at $0.08 per GB-month", "text": "Starting at $0.08 per GB-month" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Persistent storage mounted in a Vercel Sandbox.", "docs_url": null, "feature": "Drive Storage", "group": "Vercel Compute", "section": "Vercel Drives", "values": [ { "included": "15 GB (lifetime) included", "plan": "Hobby", "price": null, "text": "15 GB (lifetime) included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.05 per GB-month", "text": "Starting at $0.05 per GB-month" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Data read from a Drive.", "docs_url": null, "feature": "Drive Reads", "group": "Vercel Compute", "section": "Vercel Drives", "values": [ { "included": "30 GB / month included", "plan": "Hobby", "price": null, "text": "30 GB / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.0015 per GB", "text": "Starting at $0.0015 per GB" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Data written to a Drive.", "docs_url": null, "feature": "Drive Writes", "group": "Vercel Compute", "section": "Vercel Drives", "values": [ { "included": "30 GB / month included", "plan": "Hobby", "price": null, "text": "30 GB / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.004 per GB", "text": "Starting at $0.004 per GB" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Time your code is actively executing in an instance", "docs_url": null, "feature": "Daemons Active CPU", "group": "Vercel Compute", "section": "Vercel Daemons", "values": [ { "included": "5 hours / month included", "plan": "Hobby", "price": null, "text": "5 hours / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.128 per hour", "text": "Starting at $0.128 per hour" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Memory allocated to a Vercel Daemon", "docs_url": null, "feature": "Daemons Provisioned Memory", "group": "Vercel Compute", "section": "Vercel Daemons", "values": [ { "included": "420 GB-hrs / month included", "plan": "Hobby", "price": null, "text": "420 GB-hrs / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.0212 per GB-hr", "text": "Starting at $0.0212 per GB-hr" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Image storage for Vercel Functions and Vercel Sandbox.", "docs_url": null, "feature": "Vercel Container Registry Image Storage (Beta)", "group": "Vercel Compute", "section": "Vercel Container Registry Image Storage (Beta)", "values": [ { "included": "10 GB / month included", "plan": "Hobby", "price": null, "text": "10 GB / month included" }, { "included": null, "plan": "Pro", "price": "$0.10 per GB-month", "text": "$0.10 per GB-month" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Data transfer between the Vercel Network and Vercel compute products (Functions, Middleware, and Data Cache/ISR)", "docs_url": "https://vercel.com/docs/pricing/networking#fast-origin-transfer", "feature": "Fast Origin Transfer", "group": "Vercel Compute", "section": "Fast Origin Transfer", "values": [ { "included": "10 GB / month included", "plan": "Hobby", "price": null, "text": "10 GB / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.06 per GB", "text": "Starting at $0.06 per GB" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": null, "docs_url": null, "feature": "Workflow Events", "group": "Vercel Compute", "section": "Vercel Workflows", "values": [ { "included": "50K events / month included", "plan": "Hobby", "price": null, "text": "50K events / month included" }, { "included": null, "plan": "Pro", "price": "$20 per 1,000,000 events", "text": "$20 per 1,000,000 events" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": null, "docs_url": null, "feature": "Workflow Storage Writes", "group": "Vercel Compute", "section": "Vercel Workflows", "values": [ { "included": null, "plan": "Hobby", "price": null, "text": "1 GB" }, { "included": null, "plan": "Pro", "price": "$0.50 per GB", "text": "$0.50 per GB" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": null, "docs_url": null, "feature": "Workflow Storage Retention", "group": "Vercel Compute", "section": "Vercel Workflows", "values": [ { "included": null, "plan": "Hobby", "price": null, "text": "Not available" }, { "included": null, "plan": "Pro", "price": "$0.50 per GB-month", "text": "$0.50 per GB-month" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": null, "docs_url": null, "feature": "API Operations", "group": "Vercel Compute", "section": "Vercel Queues (Beta)", "values": [ { "included": "1M / month included", "plan": "Hobby", "price": null, "text": "1M / month included" }, { "included": null, "plan": "Pro", "price": "Starting at $0.60 per 1M", "text": "Starting at $0.60 per 1M" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Custom" } ] }, { "description": "Execute functions on a schedule.", "docs_url": null, "feature": "Cron Jobs", "group": "Vercel Compute", "section": "Cron Jobs", "values": [ { "included": null, "plan": "Hobby", "price": null, "text": "Included" }, { "included": null, "plan": "Pro", "price": null, "text": "Included" }, { "included": null, "plan": "Enterprise", "price": null, "text": "Included" } ] } ], "listed_count": 153, "observed_at_ms": 1792700000000, "plan_names": [ "Hobby", "Pro", "Enterprise" ], "plans": [ { "best_for": "The perfect starting place for your web app or personal project.", "name": "Hobby", "price": "$0/mo." }, { "best_for": "Everything you need to build and scale your app.", "name": "Pro", "price": "$20/mo." }, { "best_for": "Critical security, performance, observability, platform SLAs, and support.", "name": "Enterprise", "price": "Custom" } ], "query": { "group": "Compute", "include_faqs": false, "q": null }, "source_url": "https://vercel.com/pricing.md" } ``` ### List ai gateway models - Capability: `developer-documentation/list_ai_gateway_models` - Description: Every model in the Vercel AI Gateway catalog (GET /ai-gateway/models.md, about 400 models) with id, creator, type, context window, input, output and cached-input prices per million tokens, serving providers, capability tags, zero data retention, description and detail URL. `provider` matches the creator or any serving provider; `type`, `capability` and `q` narrow it. Paginates with `offset`. - Instructions: To compare AI Gateway models and prices, or find which models a provider serves; read one model's page with `get_ai_gateway_model`. - Cost: 5 credits per call - Capability file: [List ai gateway models](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_ai_gateway_models) Accepted options: - `capability` (string): Capability tag, e.g. `vision`, `reasoning`, `tool-use`, `open-weights`. Example: `` - `limit` (number): Results per call, 1 to 500. Defaults to 25. Example: `10` - `offset` (number): Skip this many matches; pass the previous `next_offset` (also the continuation). Example: `10` - `provider` (string): Creator or serving provider, e.g. `openai`, `anthropic`, `bedrock` (case-insensitive). Example: `` - `q` (string): Words that must all appear in the id, tags or description, e.g. `claude` or `embedding`. Example: `` - `type` (string): Model type as listed in `types`, e.g. `chat`, `embedding`, `image`. Example: `` Response schema example: ```json { "count": 5, "listed_count": 416, "models": [ { "cached_input_price_per_million": 0.13, "capabilities": [ "file-input", "implicit-caching", "reasoning", "tool-use", "vision", "web-search", "structured-output" ], "context_text": "400K", "context_window": 400000, "creator": "openai", "description": "GPT‑5.1-Codex-Max is purpose-built for agentic coding.", "id": "openai/gpt-5.1-codex-max", "input_price_per_million": 1.25, "max_output_tokens": 128000, "output_price_per_million": 10, "providers": [ "azure" ], "rank": 1, "type": "chat", "url": "https://vercel.com/ai-gateway/models/gpt-5.1-codex-max", "zero_data_retention": true }, { "cached_input_price_per_million": 0.03, "capabilities": [ "file-input", "implicit-caching", "reasoning", "tool-use", "vision", "web-search", "structured-output" ], "context_text": "400K", "context_window": 400000, "creator": "openai", "description": "GPT-5.1 Codex mini is a smaller, faster, and cheaper version of GPT-5.1 Codex.", "id": "openai/gpt-5.1-codex-mini", "input_price_per_million": 0.25, "max_output_tokens": 128000, "output_price_per_million": 2, "providers": [ "azure" ], "rank": 2, "type": "chat", "url": "https://vercel.com/ai-gateway/models/gpt-5.1-codex-mini", "zero_data_retention": true }, { "cached_input_price_per_million": 0.13, "capabilities": [ "tool-use", "implicit-caching", "file-input", "reasoning", "vision", "web-search", "fast", "structured-output" ], "context_text": "400K", "context_window": 400000, "creator": "openai", "description": "An upgraded version of GPT-5 that adapts thinking time more precisely to the question to spend more time on complex questions and respond more quickly to simpler tasks.", "id": "openai/gpt-5.1-thinking", "input_price_per_million": 1.25, "max_output_tokens": 128000, "output_price_per_million": 10, "providers": [ "openai", "azure" ], "rank": 3, "type": "chat", "url": "https://vercel.com/ai-gateway/models/gpt-5.1-thinking", "zero_data_retention": true }, { "cached_input_price_per_million": 0.17, "capabilities": [ "file-input", "implicit-caching", "reasoning", "tool-use", "vision", "web-search", "structured-output", "websockets" ], "context_text": "400K", "context_window": 400000, "creator": "openai", "description": "GPT-5.2 is OpenAI's best general-purpose model, part of the GPT-5 flagship model family. It's their most intelligent model yet for both general and agentic tasks.", "id": "openai/gpt-5.2", "input_price_per_million": 1.75, "max_output_tokens": 128000, "output_price_per_million": 14, "providers": [ "azure", "openai" ], "rank": 4, "type": "chat", "url": "https://vercel.com/ai-gateway/models/gpt-5.2", "zero_data_retention": true }, { "cached_input_price_per_million": null, "capabilities": [ "tool-use", "vision", "reasoning", "file-input", "web-search", "structured-output" ], "context_text": "400K", "context_window": 400000, "creator": "openai", "description": "Version of GPT-5.2 that produces smarter and more precise responses.", "id": "openai/gpt-5.2-pro", "input_price_per_million": 21, "max_output_tokens": 128000, "output_price_per_million": 168, "providers": [ "openai" ], "rank": 5, "type": "chat", "url": "https://vercel.com/ai-gateway/models/gpt-5.2-pro", "zero_data_retention": true } ], "next_offset": 5, "observed_at_ms": 1792700000000, "query": { "capability": null, "limit": 5, "offset": 0, "provider": "openai", "q": null, "type": "chat" }, "source_url": "https://vercel.com/ai-gateway/models.md", "total_count": 42, "types": [ "chat", "embedding", "video", "evaluation", "image", "reranking", "speech", "transcription", "realtime", "tool" ] } ``` ### List blog posts - Capability: `developer-documentation/list_blog_posts` - Description: Vercel blog posts newest first from the blog index (GET /blog.md, every post and customer story with publication date, category and summary). `q` matches title, slug and summary words, `category` (Engineering, Company News, Customers, ...) and `since`/`until` narrow it. Paginates with `offset`. - Instructions: To find Vercel blog posts on a topic or from a period; read one with `get_page` using the returned `path`. - Cost: 5 credits per call - Capability file: [List blog posts](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_blog_posts) Accepted options: - `category` (string): Category as listed in `categories`, e.g. `Engineering` (case-insensitive). Example: `` - `limit` (number): Results per call, 1 to 100. Defaults to 20. Example: `10` - `offset` (number): Skip this many matches; pass the previous `next_offset` (also the continuation). Example: `10` - `q` (string): Words that must all appear in title, slug or summary. Example: `` - `since` (string): Only posts on or after this date. Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` - `until` (string): Only posts on or before this date. Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` Response schema example: ```json { "categories": [ "Engineering", "Company News", "Customer stories", "Security", "Field Engineering", "Community", "v0", "Changelog" ], "count": 5, "declared_count": 621, "listed_count": 621, "next_offset": 5, "observed_at_ms": 1792700000000, "posts": [ { "category": "Engineering", "markdown_url": "https://vercel.com/blog/making-every-harness-durable.md", "path": "blog/making-every-harness-durable", "published": "2026-10-19", "slug": "making-every-harness-durable", "summary": "durable-harness makes Pi, OpenCode, Claude Code, and Codex durable on Vercel, Postgres, or your laptop, so agent sessions survive crashes and timeouts.", "title": "Making every harness durable", "url": "https://vercel.com/blog/making-every-harness-durable" }, { "category": null, "markdown_url": "https://vercel.com/blog/vercel-and-shopify-make-agents-first-class-shoppers.md", "path": "blog/vercel-and-shopify-make-agents-first-class-shoppers", "published": "2026-10-16", "slug": "vercel-and-shopify-make-agents-first-class-shoppers", "summary": "Vercel Shop is now generally available: an open source Next.js template for Shopify with product information and shopping tools designed for agents.", "title": "Vercel and Shopify make agents first-class shoppers", "url": "https://vercel.com/blog/vercel-and-shopify-make-agents-first-class-shoppers" }, { "category": "Company News", "markdown_url": "https://vercel.com/blog/vercel-ship-2026-recap.md", "path": "blog/vercel-ship-2026-recap", "published": "2026-10-15", "slug": "vercel-ship-2026-recap", "summary": "For a decade, Vercel has shaped how the web gets built. Now, we’re doing the same for agents. Vercel Ship 2026 brought together over 10,000 developers, founders, and executives across five cities to build the future of Agentic Infastructure.", "title": "Vercel Ship 2026 recap", "url": "https://vercel.com/blog/vercel-ship-2026-recap" }, { "category": null, "markdown_url": "https://vercel.com/blog/ai-gateway-production-index-october-2026.md", "path": "blog/ai-gateway-production-index-october-2026", "published": "2026-10-15", "slug": "ai-gateway-production-index-october-2026", "summary": "The October 2026 AI Gateway production index covering data from September 2026: Open-weight models process more than seven in ten gateway tokens and take nearly one in four dollars; AI spend is up 13x while the cost per token halves", "title": "Open weight takes 71.5% of tokens and 23% of spend", "url": "https://vercel.com/blog/ai-gateway-production-index-october-2026" }, { "category": null, "markdown_url": "https://vercel.com/blog/vercel-for-enterprise.md", "path": "blog/vercel-for-enterprise", "published": "2026-10-15", "slug": "vercel-for-enterprise", "summary": "Vercel for Enterprise gives you a single deployment destination for engineers and citizen developers, with central governance for access, providers, models, data retention, token budgets, integrations, and policies, managed through your existing IdP.", "title": "Vercel for Enterprise", "url": "https://vercel.com/blog/vercel-for-enterprise" } ], "query": { "category": null, "limit": 5, "offset": 0, "q": null, "since": null, "until": null }, "source_url": "https://vercel.com/blog.md", "total_count": 621 } ``` ### List marketplace integrations - Capability: `developer-documentation/list_marketplace_integrations` - Description: Integrations listed on the Vercel Marketplace page (GET /marketplace.md): section (native Marketplace integrations or external integrations), name, slug, URL, description and products. `q` matches name, description and product words; `section` narrows it. Paginates with `offset`. - Instructions: To find which databases, AI, observability, auth, CMS or commerce services integrate with Vercel; product pages under /marketplace/ have no Markdown twin, so details come from the integration's own docs. - Cost: 5 credits per call - Capability file: [List marketplace integrations](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_marketplace_integrations) Accepted options: - `limit` (number): Results per call, 1 to 500. Defaults to 50. Example: `10` - `offset` (number): Skip this many matches; pass the previous `next_offset` (also the continuation). Example: `10` - `q` (string): Words, e.g. `postgres` or `feature flags`. Example: `` - `section` (string): Section name or part of it: `Marketplace` or `External`. Example: `
` Response schema example: ```json { "count": 8, "integrations": [ { "description": "Postgres serverless platform designed to build reliable and scalable apps", "name": "Neon", "products": [ "Neon" ], "section": "Marketplace integrations", "slug": "neon", "url": "https://vercel.com/marketplace/neon" }, { "description": "Serverless, reliable, secure AWS Services.", "name": "AWS", "products": [ "Amazon Aurora PostgreSQL", "Amazon Aurora DSQL", "Amazon DynamoDB", "Amazon OpenSearch Serverless", "Amazon S3 - Object storage", "Amazon S3 Tables", "Amazon S3 Vectors" ], "section": "Marketplace integrations", "slug": "aws", "url": "https://vercel.com/marketplace/aws" }, { "description": "Open-source Postgres development platform that scales to millions.", "name": "Supabase", "products": [ "Supabase" ], "section": "Marketplace integrations", "slug": "supabase", "url": "https://vercel.com/marketplace/supabase" }, { "description": "PostgreSQL re-engineered for B2B apps", "name": "Nile", "products": [ "Nile" ], "section": "Marketplace integrations", "slug": "nile", "url": "https://vercel.com/marketplace/nile" }, { "description": "Managed PostgreSQL 17 with pooling. Start for Free", "name": "Prisma Postgres", "products": [ "Prisma Postgres" ], "section": "Marketplace integrations", "slug": "prisma", "url": "https://vercel.com/marketplace/prisma" }, { "description": "Postgres serverless platform designed to build reliable and scalable apps", "name": "Neon", "products": [], "section": "External integrations", "slug": "neon", "url": "https://vercel.com/marketplace/neon" }, { "description": "Open-source Postgres development platform that scales to millions.", "name": "Supabase", "products": [], "section": "External integrations", "slug": "supabase", "url": "https://vercel.com/marketplace/supabase" }, { "description": "Build postgres-based realtime backends", "name": "Thin Backend", "products": [], "section": "External integrations", "slug": "thin", "url": "https://vercel.com/marketplace/thin" } ], "listed_count": 133, "next_offset": null, "observed_at_ms": 1792700000000, "query": { "limit": 50, "offset": 0, "q": "postgres", "section": null }, "sections": [ "Marketplace integrations", "External integrations" ], "source_url": "https://vercel.com/marketplace.md", "total_count": 8 } ``` ### List rest api endpoints - Capability: `developer-documentation/list_rest_api_endpoints` - Description: The Vercel REST API endpoint index from the reference page (GET /docs/rest-api.md, about 450 endpoints): group, HTTP method, path, summary and the docs page for each. `q` matches method, path, summary and group words; `group` and `method` narrow it. Paginates with `offset`. - Instructions: To find the Vercel REST API endpoint for a task (deployments, projects, domains, env vars), then read its parameters with `get_page` using `docs_path`. - Cost: 5 credits per call - Capability file: [List rest api endpoints](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_rest_api_endpoints) Accepted options: - `group` (string): Group heading as listed in `groups`, e.g. `Deployments` (case-insensitive). Example: `` - `limit` (number): Results per call, 1 to 500. Defaults to 25. Example: `10` - `method` (string): HTTP method: GET, POST, PATCH, PUT or DELETE. Example: `` - `offset` (number): Skip this many matches; pass the previous `next_offset` (also the continuation). Example: `10` - `q` (string): Words, e.g. `deployment events` or `env`. Example: `deployment events` Response schema example: ```json { "count": 5, "endpoints": [ { "docs_path": "docs/rest-api/deployments/get-deployment-events", "docs_url": "https://vercel.com/docs/rest-api/deployments/get-deployment-events", "group": "Deployments", "markdown_url": "https://vercel.com/docs/rest-api/deployments/get-deployment-events.md", "method": "GET", "path": "/v3/deployments/{idOrUrl}/events", "summary": "Get deployment events" }, { "docs_path": "docs/rest-api/deployments/get-a-deployment-by-id-or-url", "docs_url": "https://vercel.com/docs/rest-api/deployments/get-a-deployment-by-id-or-url", "group": "Deployments", "markdown_url": "https://vercel.com/docs/rest-api/deployments/get-a-deployment-by-id-or-url.md", "method": "GET", "path": "/v13/deployments/{idOrUrl}", "summary": "Get a deployment by ID or URL" }, { "docs_path": "docs/rest-api/deployments/list-deployment-files", "docs_url": "https://vercel.com/docs/rest-api/deployments/list-deployment-files", "group": "Deployments", "markdown_url": "https://vercel.com/docs/rest-api/deployments/list-deployment-files.md", "method": "GET", "path": "/v6/deployments/{id}/files", "summary": "List Deployment Files" }, { "docs_path": "docs/rest-api/deployments/get-deployment-file-contents", "docs_url": "https://vercel.com/docs/rest-api/deployments/get-deployment-file-contents", "group": "Deployments", "markdown_url": "https://vercel.com/docs/rest-api/deployments/get-deployment-file-contents.md", "method": "GET", "path": "/v8/deployments/{id}/files/{fileId}", "summary": "Get Deployment File Contents" }, { "docs_path": "docs/rest-api/deployments/list-deployments", "docs_url": "https://vercel.com/docs/rest-api/deployments/list-deployments", "group": "Deployments", "markdown_url": "https://vercel.com/docs/rest-api/deployments/list-deployments.md", "method": "GET", "path": "/v7/deployments", "summary": "List deployments" } ], "groups": [ "Access Groups", "Ai Gateway", "Artifacts", "Billing", "Bulk Redirects", "Checks V2", "Networking", "Connect", "Daemons", "Deployments", "DNS", "Other", "Domains Registrar", "Domains", "Drains", "CDN Cache", "Global Config", "Environment", "User", "Feature Flags", "Integrations", "Marketplace", "Authentication", "Kms", "Logs", "Microfrontends", "Observability", "Organizations", "Projectmembers", "Project Routes", "Projects", "Rolling Release", "Sandboxes", "Security", "Storage", "Teams", "VCR", "Vercel Ci", "Web Analytics", "Webhooks", "Aliases", "Certs" ], "listed_count": 458, "next_offset": null, "observed_at_ms": 1792700000000, "query": { "group": "Deployments", "limit": 10, "method": "GET", "offset": 0, "q": null }, "source_url": "https://vercel.com/docs/rest-api.md", "total_count": 5 } ``` ### List templates - Capability: `developer-documentation/list_templates` - Description: Templates from the Vercel template gallery (GET /templates.md, or /templates/{filter}.md for one filter) with title, framework, slug, URL and description. `framework` and `use_case` take gallery filter slugs (`next.js`, `nuxt`, `svelte`, `astro`, `ai`, `starter`, `ecommerce`, `blog`, ...); both together return templates in both lists. `q` matches title and description words. Unknown filter slugs are invalid input. Paginates with `offset`. - Instructions: To find a deployable Vercel starter for a framework or use case; read its README, repository and deploy link with `get_page` using the returned `path`. - Cost: 5 credits per call - Capability file: [List templates](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/list_templates) Accepted options: - `framework` (string): Gallery framework filter slug, e.g. `next.js`, `nuxt`, `svelte`, `astro`, `remix`. Example: `next.js` - `limit` (number): Results per call, 1 to 500. Defaults to 24. Example: `10` - `offset` (number): Skip this many matches; pass the previous `next_offset` (also the continuation). Example: `10` - `q` (string): Words that must all appear in title, framework or description. Example: `` - `use_case` (string): Gallery use-case filter slug, e.g. `ai`, `starter`, `ecommerce`, `blog`. Example: `` Response schema example: ```json { "count": 5, "next_offset": 5, "observed_at_ms": 1792700000000, "query": { "framework": "next.js", "limit": 5, "offset": 0, "q": "blog", "use_case": null }, "sources": [ { "count": 348, "title": "Next.js starter templates and themes", "url": "https://vercel.com/templates/next.js.md" } ], "templates": [ { "description": "A statically generated blog example using Next.js and Markdown.", "framework": "next.js", "markdown_url": "https://vercel.com/templates/next.js/blog-starter-kit.md", "path": "templates/next.js/blog-starter-kit", "slug": "blog-starter-kit", "title": "Blog Starter Kit", "url": "https://vercel.com/templates/next.js/blog-starter-kit" }, { "description": "An Incremental Static Regeneration Blog Example Using Next.js and WordPress", "framework": "next.js", "markdown_url": "https://vercel.com/templates/next.js/isr-blog-nextjs-wordpress.md", "path": "templates/next.js/isr-blog-nextjs-wordpress", "slug": "isr-blog-nextjs-wordpress", "title": "ISR Blog with Next.js and WordPress", "url": "https://vercel.com/templates/next.js/isr-blog-nextjs-wordpress" }, { "description": "A blog template with Next.js 13 App Router, Contentlayer, Tailwind CSS and dark mode.", "framework": "next.js", "markdown_url": "https://vercel.com/templates/next.js/nextjs-contentlayer.md", "path": "templates/next.js/nextjs-contentlayer", "slug": "nextjs-contentlayer", "title": "Next.js Contentlayer Blog Starter", "url": "https://vercel.com/templates/next.js/nextjs-contentlayer" }, { "description": "Easily create a portfolio with Next.js and Markdown.", "framework": "next.js", "markdown_url": "https://vercel.com/templates/next.js/nextjs-portfolio.md", "path": "templates/next.js/nextjs-portfolio", "slug": "nextjs-portfolio", "title": "Next.js Portfolio with Blog", "url": "https://vercel.com/templates/next.js/nextjs-portfolio" }, { "description": "Next.js blog using Markdown for content.", "framework": "next.js", "markdown_url": "https://vercel.com/templates/next.js/tailwind-css-starter-blog.md", "path": "templates/next.js/tailwind-css-starter-blog", "slug": "tailwind-css-starter-blog", "title": "Tailwind CSS Blog", "url": "https://vercel.com/templates/next.js/tailwind-css-starter-blog" } ], "total_count": 17 } ``` ### Search docs - Capability: `developer-documentation/search_docs` - Description: Search or list Vercel documentation pages from the docs semantic sitemap (GET /docs/sitemap.md, about 1,700 pages with type, last-modified date, summary, prerequisites and topics). `q` keyword-ranks pages by title, path, topics and summary (every word must match); without `q` the pages come in docs-tree order. `group` and `page_type` narrow the list. Paginates with `offset`. - Instructions: To find the right Vercel docs page for a topic (functions, ISR, domains, AI Gateway, Sandbox, REST API endpoints), then read it with `get_page` using the returned `path`. - Cost: 5 credits per call - Capability file: [Search docs](https://firecrawl.dev/alexandria/agents/providers/vercel-com/developer-documentation/search_docs) Accepted options: - `group` (string): Docs area exactly as listed in `groups`, e.g. `Compute`, `AI`, `CDN` (case-insensitive). Example: `` - `limit` (number): Results per call, 1 to 100. Defaults to 10. Example: `10` - `offset` (number): Skip this many matches; pass the previous `next_offset` (also the continuation). Example: `10` - `page_type` (string): Sitemap page type: `How-to`, `Conceptual`, `Reference` or `Tutorial` (case-insensitive). Example: `How-to` - `q` (string): Keywords, e.g. `streaming functions` or `custom domain dns`. Example: `streaming functions` Response schema example: ```json { "count": 2, "groups": [ "APIs & SDKs", "Access", "AI", "Build & Deploy", "CDN", "Collaboration", "Compute", "Integrations", "External Platforms", "Observability", "Platform", "Pricing", "Rest API", "Security", "Storage", "REST API Reference" ], "listed_count": 1706, "next_offset": null, "observed_at_ms": 1792700000000, "query": { "group": null, "limit": 5, "offset": 0, "page_type": null, "q": "streaming functions" }, "results": [ { "depth": 1, "group": "Compute", "last_updated": "2026-09-01", "markdown_url": "https://vercel.com/docs/functions/streaming-functions.md", "page_type": "How-to", "path": "docs/functions/streaming-functions", "prerequisites": [ "Functions" ], "rank": 1, "score": 15, "summary": "Learn how to stream responses from Vercel Functions.", "title": "Streaming", "topics": [ "functions", "streaming functions" ], "url": "https://vercel.com/docs/functions/streaming-functions" }, { "depth": 1, "group": "Compute", "last_updated": "2026-08-10", "markdown_url": "https://vercel.com/docs/functions/websockets.md", "page_type": "How-to", "path": "docs/functions/websockets", "prerequisites": [ "Functions" ], "rank": 2, "score": 7, "summary": "Serve WebSocket connections in Vercel Functions for realtime features like chat, collaboration, and AI streaming.", "title": "WebSockets", "topics": [ "functions", "websockets" ], "url": "https://vercel.com/docs/functions/websockets" } ], "source_url": "https://vercel.com/docs/sitemap.md", "total_count": 2 } ```