Provider pricing

Vercel AI Gateway AI API pricing

Vercel AI Gateway has 2 priced models in the public snapshot. For 1,000 input and 500 output tokens, GPT-4o (via Vercel) has the lowest recorded request cost at $0.0075, with $2.5 input and

Vercel AI Gateway AI API pricing

0 output per million tokens.

Founded2024 (Gateway GA — Vercel founded 2015)
HeadquartersSan Francisco, CA
Tracked models2

Best for

Vercel apps and teams that want provider-neutral routing without lock-in.

Strengths

  • 100+ models, one endpoint, one key — pass-through pricing
  • Automatic failover and load balancing across providers
  • BYOK supported — bring your own provider keys for free routing
  • Native AI SDK, observability, and caching built in

Tracked Vercel AI Gateway models

ModelInput $/MOutput $/MContextTierBest for
GPT-4o (via Vercel)$2.50$10.00128,000FlagshipRouted pass-through pricing
Claude 3.5 Sonnet (via Vercel)$3.00$15.00200,000FlagshipRouted via Vercel AI Gateway

Last updated: · Source: No official pricing URL recorded · Methodology

Frequently asked questions

How much does the Vercel AI Gateway API cost?

Vercel AI Gateway has 2 priced models in the public snapshot. For 1,000 input and 500 output tokens, GPT-4o (via Vercel) has the lowest recorded request cost at $0.0075, with $2.5 input and $10 output per million tokens.

Which Vercel AI Gateway model is cheapest?

GPT-4o (via Vercel) is the lowest-cost recorded model for the 1,000-input/500-output example. Prices are $2.5 input and $10 output per million tokens; different workloads may change the ranking.

Does Vercel AI Gateway have cached or batch prices?

Cached input: not separately recorded. Batch: not recorded in this dataset. Eligibility and cache-write charges depend on the provider; these discounts are not automatically stacked.

How often are provider prices verified?

The live pricing table synchronizes stored model records daily; public file snapshots update when the site is rebuilt. Synchronization is not independent provider verification. Snapshot updated 2026-10-31; only explicit per-model dates are verification records.