{ "name": "Vercel AI Gateway", "slug": "vercel-ai-gateway", "website_url": "https://vercel.com/ai-gateway", "vendor_description": "\"AI Gateway provides a unified API to access hundreds of AI models through a single endpoint, with built-in budgets, usage monitoring, and fallbacks.\"", "categories": [ "ai-gateways" ], "summary": "Vercel AI Gateway is a unified REST API that routes requests to hundreds of AI models across multiple providers through a single endpoint, with built-in automatic fallback, load balancing, spend limits, and observability logging. It launched in May 2025 and reached general availability in August 2025, and is used by teams at v0.app, Browserbase, and Perplexity. Pricing is usage-based per token with a free tier offering $5 of credits every 30 days on a rate-limited subset of models; paid tiers unlock BYOK, zero data retention routing, and higher rate limits. The service holds SOC 2 Type 2, ISO 27001, HIPAA, GDPR, and PCI DSS certifications, and exposes OpenAI-compatible, Anthropic-compatible, and native SDKs for TypeScript and Python.", "capabilities": { "supported_actions": [ "unified_chat_completions", "openai_compatible_api", "anthropic_messages_api_compatible", "openai_responses_api_compatible", "model_routing", "automatic_fallback", "load_balancing", "prompt_caching", "spend_limits", "budgets", "rate_limiting", "observability_logging", "tracing", "byo_provider_keys", "virtual_keys", "provider_allowlist", "zero_data_retention", "disallow_prompt_training", "routing_rules", "model_rewrite_rules", "model_deny_rules", "custom_reporting", "spend_reporting_by_user_model_tag", "embeddings", "reranking", "image_generation", "video_generation", "speech_tts_stt", "realtime_speech_to_speech", "web_search_augmentation", "dynamic_model_discovery", "oidc_authentication", "provider_timeout_config", "service_tier_selection" ], "supported_regions": [], "supported_languages": [], "input_types": [ "chat completions", "text completions", "embeddings", "reranking", "image generation", "video generation", "audio/speech", "realtime speech-to-speech" ], "output_types": [ "streaming (SSE)", "JSON", "OpenAI-compatible response", "Anthropic-compatible response", "OpenAI Responses API-compatible response" ], "webhooks_supported": true, "sandbox_available": false, "sdk_languages": [ "TypeScript/JavaScript", "TypeScript/JavaScript (OpenAI-compatible drop-in)", "Python (OpenAI-compatible drop-in)", "TypeScript (Anthropic-compatible drop-in)" ], "mcp_server_available": true }, "integration": { "api_style": "rest", "base_url": "https://ai-gateway.vercel.sh/v1", "api_version": "v1", "versioning_scheme": "url", "stability": "ga", "deprecation_policy_url": "https://vercel.com/docs/release-phases", "auth_methods": [ "api_key", "jwt" ], "auth_docs_url": "https://vercel.com/docs/ai-gateway/authentication-and-byok/authentication", "idempotency_supported": null, "error_format": "openai-compatible", "webhook_signing": null, "webhook_events_url": null, "rate_limit_requests": null, "rate_limit_window": null, "sdk_packages": [ { "package": "ai", "language": "TypeScript/JavaScript", "official": true, "repo_url": "https://github.com/vercel/ai" }, { "package": "@ai-sdk/gateway", "language": "TypeScript/JavaScript", "official": true, "repo_url": "https://github.com/vercel/ai" }, { "package": "openai", "language": "TypeScript/JavaScript (OpenAI-compatible drop-in)", "official": false, "repo_url": "https://github.com/openai/openai-node" }, { "package": "openai", "language": "Python (OpenAI-compatible drop-in)", "official": false, "repo_url": "https://github.com/openai/openai-python" }, { "package": "@anthropic-ai/sdk", "language": "TypeScript (Anthropic-compatible drop-in)", "official": false, "repo_url": "https://github.com/anthropic/anthropic-sdk-typescript" } ], "mcp_url": "https://mcp.vercel.com", "quickstart_url": "https://vercel.com/docs/ai-gateway/getting-started/text" }, "pricing": { "pricing_model": "usage_based", "has_published_pricing": true, "starting_price_usd": null, "price_basis": "token", "free_tier_available": true, "free_tier_limit": "$5 of credits every 30 days (subset of models only; rate-limited)", "free_tier_details": "$5 of AI Gateway Credits every 30 days for teams that have not purchased credits. Free tier covers a subset of models (not the full catalog) and is rate-limited per model. Monthly free credit stops applying once the team makes a first purchase of AI Gateway Credits.", "minimum_commitment": null, "self_serve_signup": true, "requires_sales_call": false, "requires_verification": false, "enterprise_plan_available": true, "price_points": [ { "plan": "Free", "item": "Gateway usage fee — no markup, free-tier models only, rate-limited", "amount_usd": "0.0000", "amount_percent": "0.0000", "per": "request", "currency": "USD", "source_url": "https://vercel.com/docs/ai-gateway/pricing" }, { "plan": "Paid", "item": "Gateway markup on model tokens (PAYG, zero markup)", "amount_usd": null, "amount_percent": "0.0000", "per": "% of spend", "currency": "USD", "source_url": "https://vercel.com/docs/ai-gateway/pricing" }, { "plan": "Paid", "item": "Gateway markup on model tokens with BYOK (zero markup)", "amount_usd": null, "amount_percent": "0.0000", "per": "% of spend", "currency": "USD", "source_url": "https://vercel.com/docs/ai-gateway/pricing" }, { "plan": "Pro and Enterprise", "item": "Custom Reporting — tag/user ID/quota entity ID write", "amount_usd": "0.0750", "amount_percent": null, "per": "1,000 writes", "currency": "USD", "source_url": "https://vercel.com/docs/ai-gateway/pricing" }, { "plan": "Pro and Enterprise", "item": "Custom Reporting — reporting endpoint query", "amount_usd": "5.0000", "amount_percent": null, "per": "1,000 queries", "currency": "USD", "source_url": "https://vercel.com/docs/ai-gateway/pricing" }, { "plan": "Pro and Enterprise", "item": "Team-wide provider allowlist surcharge", "amount_usd": "0.1000", "amount_percent": null, "per": "1,000 successful requests", "currency": "USD", "source_url": "https://vercel.com/docs/ai-gateway/pricing" }, { "plan": "Pro and Enterprise", "item": "Team-wide Zero Data Retention (ZDR) surcharge", "amount_usd": "0.1000", "amount_percent": null, "per": "1,000 requests", "currency": "USD", "source_url": "https://vercel.com/docs/ai-gateway/pricing" } ] }, "compliance": { "soc2": "type_2", "hipaa": true, "gdpr": true, "iso_27001": true, "pci_dss": true, "sla_published": true, "sla_url": "https://vercel.com/legal/sla", "data_retention_policy_url": "https://vercel.com/docs/ai-gateway/security-and-compliance/zdr", "documented_rate_limits": "Free tier requests are rate-limited per model with lower limits than the paid tier; a 429 is returned when exceeded. Purchasing AI Gateway Credits moves the team to the paid tier with higher rate limits. Vercel states it places no rate limits of its own on paid-tier queries - upstream provider limits may apply. Specific numeric RPM/TPM figures are not publicly documented.", "known_restrictions": [ "BYOK is only available on the paid tier (requires purchased AI Gateway Credits)", "Per-request zero data retention (ZDR) and provider allowlist are Pro and Enterprise only", "Team-wide provider allowlist incurs $0.10 per 1,000 successful requests surcharge (Pro and Enterprise)", "Team-wide Zero Data Retention incurs $0.10 per 1,000 requests surcharge (Pro and Enterprise)", "Custom Reporting API endpoint (/v1/report) is not available on Hobby or Pro-trial plans", "Custom Reporting incurs $0.075 per 1,000 tag/user ID/quota entity ID writes and $5 per 1,000 queries", "Routing rules feature is in beta and may change before GA", "Free tier limited to subset of models, not full catalog", "Free monthly credit ($5) ceases once the first credit purchase is made" ] }, "developer": { "docs_url": "https://vercel.com/docs", "api_reference_url": "https://vercel.com/login?next=%2Freference", "openapi_spec_url": null, "postman_collection_url": null, "changelog_url": "https://vercel.com/changelog", "status_page_url": "https://status.vercel.com", "llms_txt_url": "https://vercel.com/llms.txt", "markdown_docs_url": null, "rendering": "static" }, "adoption": { "launched_at": "2025-05-20", "ga_date": "2025-08-21", "github_stars": null, "github_stars_at": null, "notable_customers": [ "v0.app", "Browserbase", "Perplexity" ] }, "scores": { "agent_friendliness": 55, "pricing_transparency": 75, "setup_speed": 85, "docs_quality": 55, "procurement_friction": 90, "trust_readiness": 100, "best_for": [ "Prototypes and side projects - free to start, no sales call", "Regulated or enterprise workloads - compliance attestations and an enterprise plan", "AI agents and automation - an agent-ready surface (MCP / llms.txt)" ], "avoid_if": [] }, "sources": [ { "field": "categories", "url": "https://vercel.com/docs/ai-gateway", "excerpt": "AI Gateway provides a unified API to access hundreds of AI models through a single endpoint, with built-in budgets, usage monitoring, and fallbacks.", "confidence": "high" }, { "field": "primary_use_cases", "url": "https://vercel.com/docs/ai-gateway", "excerpt": "One key, hundreds of models. Access models from multiple providers with a single API key... High reliability. Automatically retries requests to other providers if one fails... Spend monitoring. Monitor your spending across different providers... No markup on tokens. Tokens cost the same as they would from the provider directly, with zero markup", "confidence": "high" }, { "field": "supported_actions", "url": "https://vercel.com/docs/ai-gateway/models-and-providers/provider-options", "excerpt": "You can use order, only, and sort in providerOptions.gateway to control which providers handle your requests, in what order, and how they are ranked.", "confidence": "high" }, { "field": "supported_actions", "url": "https://vercel.com/docs/ai-gateway/models-and-providers", "excerpt": "const rerankingModels = models.filter((m) => m.modelType === 'reranking');", "confidence": "high" }, { "field": "input_types", "url": "https://vercel.com/docs/ai-gateway/models-and-providers", "excerpt": "const rerankingModels = models.filter((m) => m.modelType === 'reranking');", "confidence": "high" }, { "field": "pricing_model", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "AI Gateway uses a pay-as-you-go model with no markups. Purchase AI Gateway Credits and Vercel automatically deducts charges from your balance.", "confidence": "high" }, { "field": "has_published_pricing", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "Custom Reporting: Write $0.075 / 1,000 tag/user ID/quota entity ID writes; Query $5 / 1,000 queries to the reporting endpoint... Team-wide provider allowlist $0.10 per 1,000 successful requests... Team-wide zero data retention $0.10 per 1,000 requests", "confidence": "high" }, { "field": "free_tier_available", "url": "https://vercel.com/ai-gateway", "excerpt": "When you sign up for a Vercel account, you get $5 of credits every 30 days to try out any model from our model list.", "confidence": "high" }, { "field": "free_tier_details", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "Your free credits start when you make your first AI Gateway request. To run larger workloads, you can purchase AI Gateway Credits at any time with no obligation to renew. Once you purchase credits, your account transitions to the paid tier and the monthly free credit no longer applies.", "confidence": "high" }, { "field": "vendor_description", "url": "https://vercel.com/docs/ai-gateway", "excerpt": "AI Gateway provides a unified API to access hundreds of AI models through a single endpoint, with built-in budgets, usage monitoring, and fallbacks.", "confidence": "high" }, { "field": "categories", "url": "https://vercel.com/docs/ai-gateway/observability-and-spend/observability", "excerpt": "The AI Gateway logs spend, model usage, and observability metrics related to your requests, which you can use to monitor and debug.", "confidence": "high" }, { "field": "primary_use_cases", "url": "https://vercel.com/docs/ai-gateway/models-and-providers", "excerpt": "const rerankingModels = models.filter((m) => m.modelType === 'reranking');", "confidence": "high" }, { "field": "supported_actions", "url": "https://vercel.com/docs/ai-gateway/models-and-providers/routing-rules", "excerpt": "Routing rules let you control how AI Gateway handles your team's requests at the model level. You define team-wide rules that either rewrite a request from one model to another, or deny a model so requests for it are blocked.", "confidence": "high" }, { "field": "input_types", "url": "https://vercel.com/docs/ai-gateway/getting-started", "excerpt": "Text Generation: Generate and stream text... Image Generation: Create images from text prompts... Video Generation: Create videos from text prompts... Realtime: Build low-latency, speech-to-speech voice agents... Speech: Generate spoken audio from text and transcribe audio back to text", "confidence": "high" }, { "field": "webhooks_supported", "url": "https://vercel.com/docs/spend-management", "excerpt": "You can configure a webhook URL to trigger events such as serving a static version of your site, pausing a project, or sending a Slack notification. Vercel will send a HTTPS POST request to the URL that you provide when the following events happen: When a spend amount reaches 100%; At the end of your billing cycle", "confidence": "medium" }, { "field": "pricing_model", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "For the paid tier, AI Gateway provides tokens with zero markup, including when you bring your own key.", "confidence": "high" }, { "field": "free_tier_available", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "Every Vercel team account gets access to both a free tier and a paid tier for AI Gateway Credits. The free tier includes a subset of models, not the full catalog. Free tier requests are also rate limited per model, with lower limits than the paid tier.", "confidence": "high" }, { "field": "free_tier_details", "url": "https://vercel.com/ai-gateway", "excerpt": "When you sign up for a Vercel account, you get $5 of credits every 30 days to try out any model from our model list.", "confidence": "high" }, { "field": "enterprise_plan_available", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "Team-wide provider allowlist $0.10 per 1,000 successful requests Pro and Enterprise... Zero Data Retention: Per-request zero data retention No additional cost Pro and Enterprise", "confidence": "high" }, { "field": "sdk_languages", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk", "excerpt": "The AI SDK is the recommended way to build AI-powered TypeScript applications with AI Gateway. Pass a model string like 'anthropic/claude-sonnet-4.6' directly to AI SDK functions and requests route through AI Gateway automatically.", "confidence": "high" }, { "field": "mcp_server_available", "url": "https://vercel.com/docs/agent-resources/vercel-mcp", "excerpt": "Vercel MCP is Vercel's official MCP server. It's a remote MCP with OAuth that gives AI tools secure access to your Vercel projects available at: https://mcp.vercel.com", "confidence": "high" }, { "field": "hipaa", "url": "https://vercel.com/security", "excerpt": "Vercel supports HIPAA compliance for enterprise customers. Their HIPAA report is available upon request at security.vercel.com", "confidence": "high" }, { "field": "iso_27001", "url": "https://vercel.com/security", "excerpt": "Vercel holds ISO 27001:2013 certified status.", "confidence": "high" }, { "field": "sla_published", "url": "https://vercel.com/legal/sla", "excerpt": "Vercel Inc. will use commercially reasonable efforts to make the platform as a service...available 99.99% of the time, excluding any Excused Downtime events.", "confidence": "high" }, { "field": "documented_rate_limits", "url": "https://vercel.com/ai-gateway", "excerpt": "Vercel doesn't place any rate limits on your queries — while the upstream providers may have limits, we actively work with them to maximize your limits and throughput.", "confidence": "high" }, { "field": "known_restrictions", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/rest-api", "excerpt": "Hobby and Pro-trial plans cannot use this endpoint.", "confidence": "high" }, { "field": "self_serve_signup", "url": "https://vercel.com/docs/ai-gateway/authentication-and-byok/authentication", "excerpt": "Go to the AI Gateway API Keys page in your Vercel dashboard. Click Create key and follow the steps to generate a new API key.", "confidence": "high" }, { "field": "sdk_languages", "url": "https://vercel.com/docs/ai-gateway/getting-started", "excerpt": "AI Gateway works with AI SDK v5 and v6, OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, or your preferred framework.", "confidence": "high" }, { "field": "soc2", "url": "https://vercel.com/security", "excerpt": "SOC 2 Type 2 compliant. Vercel has obtained a SOC 2 Type 2 attestation", "confidence": "high" }, { "field": "gdpr", "url": "https://vercel.com/security", "excerpt": "Vercel confirms GDPR compliance. The platform provides a Data Processing Addendum describing Technical and Organizational Security Measures.", "confidence": "high" }, { "field": "pci_dss", "url": "https://vercel.com/security", "excerpt": "Vercel maintains Self-Assessment Questionnaire (SAQ)-D Attestation of Compliance (AOC) for Service Providers and a Self-Assessment Questionnaire (SAQ)-A Attestation of Compliance (AOC) for Merchants based on PCI DSS v4.0.", "confidence": "high" }, { "field": "documented_rate_limits", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "Free tier requests are also rate limited per model, with lower limits than the paid tier. If you exceed a limit, AI Gateway returns a 429 error and you can retry after a short wait. Purchasing AI Gateway Credits moves your team to the paid tier, which raises your rate limits.", "confidence": "high" }, { "field": "known_restrictions", "url": "https://vercel.com/docs/ai-gateway/authentication-and-byok/byok", "excerpt": "BYOK is available on the paid tier. When a request with your credentials fails, AI Gateway retries it with system credentials for reliability, and that fallback usage is charged against your credits balance. To use your own provider keys, you'll need purchased AI Gateway Credits.", "confidence": "high" }, { "field": "known_restrictions", "url": "https://vercel.com/docs/ai-gateway/models-and-providers/routing-rules", "excerpt": "AI Gateway routing rules are in beta and may change before general availability. Avoid relying on them in production.", "confidence": "high" }, { "field": "auth_methods", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions", "excerpt": "The Chat Completions API supports the same authentication methods as the main AI Gateway: API key: Use your AI Gateway API key with the Authorization: Bearer header. OIDC token: Use your Vercel OIDC token with the Authorization: Bearer header.", "confidence": "high" }, { "field": "api_style", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions", "excerpt": "AI Gateway provides OpenAI Chat Completions API endpoints, letting you use multiple AI providers through a familiar interface. You can use existing OpenAI client libraries, switch to AI Gateway with a URL change, and keep your current tools and workflows without code rewrites.", "confidence": "high" }, { "field": "base_url", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions", "excerpt": "The Chat Completions API is available at the following base URL: https://ai-gateway.vercel.sh/v1", "confidence": "high" }, { "field": "api_version", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/rest-api", "excerpt": "GET /v1/models — List all available models; GET /v1/credits — Check the team's AI Gateway Credits balance", "confidence": "high" }, { "field": "versioning_scheme", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/rest-api", "excerpt": "Base URL: https://ai-gateway.vercel.sh/v1", "confidence": "high" }, { "field": "stability", "url": "https://vercel.com/docs/release-phases", "excerpt": "When the product reaches the General Availability (GA) phase, it is considered to be battle tested, and ready for use by the community.", "confidence": "high" }, { "field": "sdk_packages", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions", "excerpt": "You can use the AI Gateway's Chat Completions API with existing tools and libraries like the OpenAI client libraries and AI SDK. Point your existing client to the AI Gateway's base URL and use your AI Gateway API key or OIDC token for authentication.", "confidence": "high" }, { "field": "mcp_url", "url": "https://vercel.com/docs/agent-resources/vercel-mcp", "excerpt": "Vercel MCP is Vercel's official MCP server. It's a remote MCP with OAuth that gives AI tools secure access to your Vercel projects available at: https://mcp.vercel.com", "confidence": "high" }, { "field": "error_format", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions", "excerpt": "Error response format: { \"error\": { \"message\": \"Invalid request: missing required parameter 'model'\", \"type\": \"invalid_request_error\", \"param\": \"model\", \"code\": \"missing_parameter\" } }", "confidence": "high" }, { "field": "rate_limit_requests", "url": "https://vercel.com/blog/ai-gateway-is-now-generally-available", "excerpt": "Vercel doesn't place any rate limits on your queries — while the upstream providers may have limits, we actively work with them to maximize your limits and throughput.", "confidence": "high" }, { "field": "sla_url", "url": "https://vercel.com/legal/sla", "excerpt": "Vercel Inc. will use commercially reasonable efforts to make the platform as a service...available 99.99% of the time, excluding any Excused Downtime events.", "confidence": "high" }, { "field": "starting_price_usd", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "AI Gateway uses a pay-as-you-go model with no markups. Purchase AI Gateway Credits and Vercel automatically deducts charges from your balance.", "confidence": "high" }, { "field": "price_basis", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "AI Gateway bases its rates on the provider's list price. The charge for each request depends on the AI provider and model you select, and the number of input and output tokens processed.", "confidence": "high" }, { "field": "free_tier_limit", "url": "https://vercel.com/ai-gateway", "excerpt": "When you sign up for a Vercel account, you get $5 of credits every 30 days to try out any model from our model list.", "confidence": "high" }, { "field": "ga_date", "url": "https://vercel.com/blog/ai-gateway-is-now-generally-available", "excerpt": "AI Gateway is now generally available — battle-tested, stable, and ready for production.", "confidence": "high" }, { "field": "auth_methods", "url": "https://vercel.com/docs/ai-gateway/authentication-and-byok/authentication", "excerpt": "Every request to AI Gateway requires authentication. Vercel provides two methods: API keys and OIDC tokens.", "confidence": "high" }, { "field": "auth_docs_url", "url": "https://vercel.com/docs/ai-gateway/authentication-and-byok/authentication", "excerpt": "Every request to AI Gateway requires authentication. Vercel provides two methods: API keys and OIDC tokens.", "confidence": "high" }, { "field": "api_style", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis", "excerpt": "AI Gateway provides drop-in compatible APIs that let you switch by changing a base URL. No code rewrites required. Use the same SDKs and tools you already know, with access to 200+ models from every major provider.", "confidence": "high" }, { "field": "base_url", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/rest-api", "excerpt": "Base URL: https://ai-gateway.vercel.sh/v1", "confidence": "high" }, { "field": "api_version", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions", "excerpt": "The Chat Completions API is available at the following base URL: https://ai-gateway.vercel.sh/v1", "confidence": "high" }, { "field": "stability", "url": "https://vercel.com/blog/ai-gateway-is-now-generally-available", "excerpt": "AI Gateway is now generally available — battle-tested, stable, and ready for production.", "confidence": "high" }, { "field": "sdk_packages", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk", "excerpt": "The AI SDK is the recommended way to build AI-powered TypeScript applications with AI Gateway. Pass a model string like 'anthropic/claude-sonnet-4.6' directly to AI SDK functions and requests route through AI Gateway automatically.", "confidence": "high" }, { "field": "sdk_packages", "url": "https://github.com/vercel/ai", "excerpt": null, "confidence": "high" }, { "field": "quickstart_url", "url": "https://vercel.com/docs/ai-gateway/getting-started/text", "excerpt": "This quickstart walks you through making your first text generation request with AI Gateway.", "confidence": "high" }, { "field": "error_format", "url": "https://vercel.com/docs/ai-gateway/sdks-and-apis/rest-api", "excerpt": "Errors return a JSON body with an error field. Some endpoints additionally include a type discriminator on the error object.", "confidence": "high" }, { "field": "requires_verification", "url": "https://vercel.com/docs/ai-gateway/authentication-and-byok/authentication", "excerpt": "Go to the AI Gateway API Keys page in your Vercel dashboard. Click Create key and follow the steps to generate a new API key.", "confidence": "high" }, { "field": "data_retention_policy_url", "url": "https://vercel.com/docs/ai-gateway/security-and-compliance/zdr", "excerpt": "AI Gateway has a ZDR policy and does not retain prompts, outputs, or sensitive data. User data is immediately and permanently deleted after requests are completed. No action is needed on the user side.", "confidence": "high" }, { "field": "starting_price_usd", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "AI Gateway bases its rates on the provider's list price. The charge for each request depends on the AI provider and model you select, and the number of input and output tokens processed.", "confidence": "high" }, { "field": "free_tier_limit", "url": "https://vercel.com/docs/ai-gateway/pricing", "excerpt": "Every Vercel team account gets access to both a free tier and a paid tier for AI Gateway Credits. The free tier includes a subset of models, not the full catalog. Free tier requests are also rate limited per model, with lower limits than the paid tier.", "confidence": "high" }, { "field": "launched_at", "url": "https://vercel.com/blog/ai-gateway", "excerpt": "The Vercel AI Gateway is now available for alpha testing", "confidence": "high" }, { "field": "notable_customers", "url": "https://vercel.com/blog/ai-gateway-is-now-generally-available", "excerpt": "It's the same system that has powered v0.app for millions of users, and it's now available to you.", "confidence": "high" } ], "fields_not_found": [ "supported_regions (no explicit data residency regions documented for AI Gateway specifically)", "specific numeric rate limits (RPM/TPM) not publicly documented", "sandbox/test environment (live environment only)", "idempotency_supported", "webhook_signing", "webhook_events_url", "rate_limit_requests", "rate_limit_window", "deprecation_policy_url (AI Gateway-specific; only platform-wide release phases page exists)" ], "source_confidence": "high", "last_verified_at": "2026-06-21T00:00:00.000Z", "contribute": { "note": "This data is crowd-editable. Suggest corrections or leave a review via these endpoints - no auth required, requests are rate-limited, and every submission is reviewed before it goes live. For a field edit, {field} is any key in this response and a citation is required.", "endpoints": [ { "action": "review", "label": "Leave a review or comment", "method": "POST", "url": "https://apio.sh/api/feedback/vercel-ai-gateway", "example_body": { "kind": "review", "rating": 5, "body": "Your experience with this API…" } }, { "action": "field_edit", "label": "Suggest a correction to a field (cite a source)", "method": "POST", "url": "https://apio.sh/api/suggest/vercel-ai-gateway/{field}", "example_body": { "value": "corrected value", "citations": [ { "url": "https://source.example/page", "excerpt": "supporting quote" } ], "note": "what changed and why" } }, { "action": "new_api", "label": "Suggest a new API to add (only name is required - send as much as you can cite)", "method": "POST", "url": "https://apio.sh/api/suggest/api", "example_body": { "value": { "name": "Acme Email API", "website_url": "https://acme.example", "vendor_name": "Acme", "categories": [ "email" ], "pricing_model": "usage_based", "has_published_pricing": true, "free_tier_available": true, "price_points": [ { "plan": "Pay as you go", "item": "1,000 emails", "amount_usd": 1, "per": "1,000 emails", "source_url": "https://acme.example/pricing" } ], "soc2": "type_2", "docs_url": "https://docs.acme.example" }, "citations": [ { "url": "https://acme.example/pricing", "excerpt": "$1 per 1,000 emails" } ] }, "value_schema": [ { "field": "name", "type": "string", "label": "Product name (the only required field)" }, { "field": "website_url", "type": "string", "label": "Marketing website URL" }, { "field": "vendor_name", "type": "string", "label": "Company/vendor name behind the product" }, { "field": "vendor_description", "type": "string", "label": "One-line description, quoted from the vendor" }, { "field": "categories", "type": "string[]", "label": "Category/leaf slugs it belongs to, e.g. [\"email\",\"sms\"]" }, { "field": "primary_use_cases", "type": "string[]", "label": "What it's used for" }, { "field": "supported_actions", "type": "string[]", "label": "Concrete API actions/capabilities" }, { "field": "supported_regions", "type": "string[]", "label": "Countries/regions/data-residency" }, { "field": "supported_languages", "type": "string[]", "label": "Human/spoken languages supported" }, { "field": "input_types", "type": "string[]", "label": "Accepted input types/formats" }, { "field": "output_types", "type": "string[]", "label": "Produced output types/formats" }, { "field": "webhooks_supported", "type": "bool", "label": "Supports webhooks?" }, { "field": "sandbox_available", "type": "bool", "label": "Dedicated sandbox/test mode?" }, { "field": "sdk_languages", "type": "string[]", "label": "Languages with an official SDK" }, { "field": "mcp_server_available", "type": "bool", "label": "Official MCP server?" }, { "field": "pricing_model", "type": "enum", "label": "Pricing model", "values": [ "usage_based", "subscription", "seat_based", "hybrid", "contact_sales" ] }, { "field": "has_published_pricing", "type": "bool", "label": "Concrete prices published publicly?" }, { "field": "free_tier_available", "type": "bool", "label": "Recurring/perpetual free tier (not a trial)?" }, { "field": "free_tier_details", "type": "string", "label": "What the free tier includes" }, { "field": "minimum_commitment", "type": "string", "label": "Any stated minimum spend/commitment" }, { "field": "self_serve_signup", "type": "bool", "label": "Get an API key without talking to sales?" }, { "field": "requires_sales_call", "type": "bool", "label": "Does going live require sales?" }, { "field": "enterprise_plan_available", "type": "bool", "label": "Named enterprise tier?" }, { "field": "starting_price_usd", "type": "number", "label": "Lowest published paid entry price (USD number)" }, { "field": "price_basis", "type": "string", "label": "Unit the starting price is per, e.g. '1,000 emails'" }, { "field": "free_tier_limit", "type": "string", "label": "Free-tier ceiling in literal terms" }, { "field": "price_points", "type": "object[]", "label": "Structured prices: [{plan,item,amount_usd,amount_percent,per,source_url}]" }, { "field": "soc2", "type": "enum", "label": "SOC 2 status", "values": [ "type_2", "type_1", "in_progress", "none", "unknown" ] }, { "field": "hipaa", "type": "bool", "label": "HIPAA (e.g. BAA available)?" }, { "field": "gdpr", "type": "bool", "label": "GDPR compliance stated?" }, { "field": "iso_27001", "type": "bool", "label": "ISO 27001 certified?" }, { "field": "pci_dss", "type": "bool", "label": "PCI DSS compliant?" }, { "field": "sla_published", "type": "bool", "label": "Published SLA / uptime commitment?" }, { "field": "documented_rate_limits", "type": "string", "label": "Documented rate limits, quoted" }, { "field": "known_restrictions", "type": "string[]", "label": "Notable documented restrictions/limits" }, { "field": "auth_methods", "type": "string[]", "label": "Auth methods", "values": [ "api_key", "oauth2", "jwt", "basic", "hmac_signature", "mtls", "session" ] }, { "field": "api_style", "type": "enum", "label": "Primary API style", "values": [ "rest", "graphql", "grpc", "soap", "websocket" ] }, { "field": "base_url", "type": "string", "label": "API root/base URL" }, { "field": "api_version", "type": "string", "label": "Current API version string" }, { "field": "quickstart_url", "type": "string", "label": "Quickstart / hello-world URL" }, { "field": "docs_url", "type": "string", "label": "Developer docs URL" }, { "field": "api_reference_url", "type": "string", "label": "API reference URL" }, { "field": "openapi_spec_url", "type": "string", "label": "OpenAPI spec URL" }, { "field": "changelog_url", "type": "string", "label": "Changelog URL" }, { "field": "status_page_url", "type": "string", "label": "Status page URL" }, { "field": "notable_customers", "type": "string[]", "label": "Named public customers" }, { "field": "launched_at", "type": "string", "label": "Launch date (ISO date or year)" } ] }, { "action": "token", "label": "Optional - raise your rate limit", "method": "GET", "url": "https://apio.sh/api/feedback/token" } ] } }