ToolsJuly 30, 2026via Vercel Blog

AI Gateway: GPT-5.6 pricing and speed updates

Why it matters

OpenAI's latest model tiers are getting cheaper and faster on Vercel's gateway layer. For teams building with GPT-5.6, this changes API economics immediately and requires zero code changes.

Key signals

  • GPT-5.6 Luna: 80% price reduction to $0.2 input / $1.2 output per 1M tokens
  • GPT-5.6 Terra: 20% price reduction to $2 input / $12 output per 1M tokens
  • GPT-5.6 Sol: same pricing, fast mode now 2.5x faster (was 1.5x)
  • Vercel AI Gateway adds zero markup—pricing passes through at upstream rate
  • No code changes required; existing requests auto-upgrade to new rates and speed
  • Changes apply to both short and long context pricing
  • Published July 30, 2026

The hook

GPT-5.6 Luna just dropped 80%. Vercel's AI Gateway passes the savings straight through—no markup.

On , and are now cheaper and is faster.AI GatewayGPT-5.6 LunaGPT-5.6 TerraGPT-5.6 Sol AI Gateway adds no markup on token pricing, so these changes reach you at the upstream rate. The changes apply to both short and long context pricing. GPT-5.6 Sol keeps the same price; its fast mode now runs 2.5

The week's key stories, every Friday.

For practitioners and enthusiasts — free, in your inbox.

Free forever. No spam.