Short answer. Vercel AI Gateway is listed as Monthly credit. No card is required. The tracker is partially verified; cells marked [VERIFY] are still being checked. The full row-by-row limits are below.
Free-tier models and limits
| Model | Status | RPM | RPD | TPM | TPD | Context | Card |
|---|---|---|---|---|---|---|---|
free-tier eligible models | Monthly credit | [VERIFY] | [VERIFY] | [VERIFY] | $5/month credit | Model-dependent | No [VERIFY] |
Source: the free LLM API tracker, checked 19 Nov 2026. Where a cell says console-only or [VERIFY], the provider does not publish the value or it is still being confirmed.
What the free tier is good for
- A $5 monthly credit for eligible models
- Teams already deployed on Vercel
- Testing multiple upstream providers behind one gateway
What to watch
- The allowance is a monthly credit, not a permanent token cap.
- Rate limits are not fully published; the tracker marks them for verification.
- Upstream provider policies still apply to data and training.
How to get started
- Create an account in the Vercel AI Gateway console and generate an API key.
- Set the provider's base URL and model ID in the OpenAI SDK or your HTTP client.
- Send a small request, then read the rate-limit headers before scaling traffic.
Primary sources: vercel.com
How it compares with a flat-rate API
Free tiers are useful for evaluation, but they are not a capacity plan. Vercel AI Gateway limits the request rate and, for some models, the tokens per day. Plugsky's free plan gives new accounts 100 requests and 50K tokens/day; paid plans start at $8/month for 2M tokens/day. Builder ($60) and Scale ($120) have no monthly token cap, with fair-use concurrency and RPM. See pricing and the unlimited API guide.
Estimate when the cap binds
Use the Free API Runway Calculator to enter your requests per day and average prompt size. It converts your workload into daily tokens and shows whether the request cap or the token cap runs out first.
FAQ
Does Vercel AI Gateway have a free tier?
Vercel AI Gateway is listed as Monthly credit in the tracker. The exact allowance and whether a card is required are shown in the table above.
What are the Vercel AI Gateway rate limits?
The table records the published requests-per-minute, requests-per-day, tokens-per-minute and tokens-per-day values per model. Where a cell says console-only or [VERIFY], the provider does not publish the number or the tracker has not confirmed it yet.
Is a credit card required?
No card is required for the free allowance shown here. Check the provider console before you rely on it for production.
What happens when the free allowance runs out?
The API returns a rate-limit or quota error, usually HTTP 429. Add a paid plan or a fallback provider before that happens; the Free API Runway Calculator estimates when the cap will bind.
Is there an alternative with no monthly token cap?
Plugsky's Builder ($60/month) and Scale ($120/month) plans have no monthly token cap and no per-token overage; fair-use concurrency and RPM apply. The free plan gives new accounts 100 requests and 50K tokens/day.
Last checked 19 Nov 2026. Limits change; confirm in the Vercel AI Gateway console before relying on them for production. This page is editorial and does not rank providers by payment.