Vercel AI Gateway review: pricing, free tier, vs OpenRouter

This page is built from Vercel's AI Gateway pages, docs, public model list and status feed, the official price pages of Anthropic, OpenAI and Google, three public latency and price comparisons, and user reports on the Vercel Community forum and GitHub, all checked on October 21, 2026. Vercel's claims are labelled as its own.

What Vercel AI Gateway sells

Vercel AI Gateway is one API and one prepaid credit balance for models from many makers. Vercel's landing page says 400+ models; its public model list returned 482 entries on October 21, 2026, from 49 makers: 323 language models, 39 video, 38 image, 28 embedding, 14 speech and 12 transcription models, among others, from Claude, GPT and Gemini to Veo, Seedance, Kling and Flux.

You call it with an AI Gateway API key from any server, or with Vercel's OIDC tokens on Vercel deployments; your app does not have to run on Vercel. The gateway fails a model over to its other providers, lets you order or restrict providers per request, supports model fallbacks, and logs each request's provider, latency, tokens and cost. It became generally available on August 21, 2025.

Prices against the official APIs

Vercel says the gateway adds zero markup to provider token prices, including when you bring your own keys. For the models checked, its prices matched the makers':

Vercel's prices come from its public model list. Card processing fees are yours, some extras are billed from credits (team-wide zero data retention costs 0.10 USD per 1,000 requests), and bought credits expire after one year. Vercel's landing page showed 26 below-list promotions on October 21; one, Gemini 3.8 Flash at half price, equals Google's own price until December 31.

What public tests show

• ComputeSDK (a sandbox SDK company that does not sell a gateway) published an open benchmark on October 16, 2026: 100 requests per model family from Northern Virginia. Median time to first token through Vercel was 462 ms against 394 ms direct on Claude Haiku 4.5, and 503 ms against 412 ms on gpt-5.4-mini (OpenRouter: 463 and 634 ms). Every request succeeded. One location, short prompts.
• Zack Proser, who runs agents on both Vercel and OpenRouter, found on August 3, 2026 that DeepSeek V4 Flash cost the same on both, but gpt-oss-120b's cheapest route was 0.10 / 0.50 USD per million tokens on Vercel against 0.03 / 0.17 USD on OpenRouter, which had 17 providers for it to Vercel's 8. His conclusion: Vercel is cheaper on the same route, OpenRouter is the more capable router.
• Edgee, a competing gateway, ran a competitor's benchmark from 43 Google Cloud regions in August 2026. It measured Vercel's median overhead at 164 ms on gpt-5.4 and 193 ms on claude-sonnet-4-6: slower than Cloudflare and Edgee, faster than OpenRouter and Kong.
• Vercel says its routing adds under 20 ms and cites a Cline A/B test with 10% to 14% better P99 streaming latency. It gives no method, and both outside tests measured more.

What users report

Complaints on the Vercel Community forum are about billing state. In April 2026 a user with 29 USD of credits got "billing issue (skipping all models)" on every request, with no staff reply. In June 2026 another saw the balance shown as NaN and calls refused. In July 2026 a user got 403 on every request after buying 10 USD of credits; the help bot said Hobby teams cannot open AI Gateway billing cases, and staff fixed it two days later without naming a cause. A May 2026 thread reports free credits refused "due to abuse" on many models.

GitHub issue #11280 on vercel/ai reports that requests with a team's own provider keys fail with "Insufficient funds" at a 0 USD balance. A Vercel team member closed it on August 10, 2026 as intended, because a failed BYOK request falls back to Vercel's credentials and is billed to credits.

MCP, Agent Skills and coding agents

Vercel's official MCP server at mcp.vercel.com searches its docs, manages projects and deployments, and reads logs, with setup for Claude Code, Codex CLI, Cursor, VS Code, OpenCode and others. Its tool reference has no AI Gateway category and says it does not create AI Gateway API keys. For MCP in your own app, Vercel documents the AI SDK's MCP client (@ai-sdk/mcp), which passes any MCP server's tools to gateway models. Passing remote MCP servers inside an API request is not documented, and message batches do not support them.

Vercel's skills.sh directory lists official Agent Skills such as ai-sdk, vercel-cli and vercel-deploy, plus a Vercel plugin for coding agents. None is specific to AI Gateway, and the Anthropic Messages docs do not mention Anthropic's Skills API.

npx vercel@latest ai-gateway setup detects installed agents, shows a diff before writing, stores the key in the macOS Keychain and configures 29 of them, including Claude Code, Codex, Cursor, Cline, Kilo Code, OpenCode and Zed; Roo Code has a manual guide. The API speaks OpenAI Chat Completions, OpenAI Responses (tools, structured outputs, reasoning, prompt caching) and Anthropic Messages (tools, extended thinking, cache_control, token counting, batches in early access). Perplexity and Parallel web search work with any model through the AI SDK. There are AI SDK packages for TypeScript and Python, guides for LangChain, LiteLLM and Pydantic AI, and an llms.txt.

Privacy, terms and who runs it

Vercel Inc. of San Francisco raised a 300 million USD Series F at a 9.3 billion USD valuation on September 30, 2025. Vercel says it does not train on prompts and the gateway keeps no prompt or response content after the request; it logs metadata and keeps routing details for 30 days. Zero data retention routing, provider allowlists and regional inference are available, several only on Pro or Enterprise. In the status feed's last 50 incidents, from May 23 to October 12, 2026, one touched AI Gateway: a 30-minute error for teams with 2FA on July 15. The docs state no minimum top-up and no refund policy.

How it compares with OpenRouter, Cloudflare and Eden AI

• OpenRouter also bills at list price but adds 5.5% when you buy credits on its Standard plan; it has more providers per open-weight model, and free models.
• Cloudflare AI Gateway is free in front of your own keys; its Unified Billing credits carry a 5% purchase fee and a cap of 200 requests per minute per gateway.
• Eden AI adds a 5.5% platform fee, but also sells OCR, speech and translation APIs and has an EU-only endpoint.
• Requesty adds 5% to each top-up.

Who should skip it

Skip it if you want to run only on your own provider keys without prepaying Vercel, need a free tier that reliably reaches flagship models, or are on the Hobby plan and cannot wait days for a billing fix. Teams shopping between many hosts of open-weight models will find fewer providers per model than on OpenRouter. For teams already on Vercel or the AI SDK, it is one of the few relays that adds nothing to list prices.