
AI Gateway: GPT-5.6 pricing and speed updates
Quick Answer
AI Gateway has announced significant updates for GPT-5.6 models: Luna sees an 80% price reduction to $0.2 per million tokens, Terra is reduced by 20% to $2 per million tokens, and Sol's fast mode is now 2.5x faster without a price change.
Quick Take
These adjustments apply to both short and long context pricing, benefiting users without requiring code changes.
Key Points
- GPT-5.6 Luna price reduced by 80% to $0.2 per million tokens.
- GPT-5.6 Terra price reduced by 20% to $2 per million tokens.
- GPT-5.6 Sol's fast mode is now 2.5x faster, unchanged pricing.
- No markup on token pricing ensures direct upstream rates.
- Changes apply to both short and long context pricing.
📖 Reader Mode
~1 min readOn AI Gateway, GPT-5.6 Luna and GPT-5.6 Terra are now cheaper and GPT-5.6 Sol is faster.
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.
Model | Change | Input: Short context (per 1M tokens) | Output: Short context (per 1M tokens) |
|---|---|---|---|
| 80% price reduction | $0.2 | $1.2 |
| 20% price reduction | $2 | $12 |
| Same price, fast mode now 2.5x faster (up from 1.5x) | Unchanged | Unchanged |
GPT-5.6 Sol keeps the same price; its fast mode now runs 2.5x faster, up from 1.5x. Model IDs are unchanged, so existing requests get the new rates and speed with no code change.
See full pricing detail on AI Gateway.
— Originally published at vercel.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Vercel AI
See more →
The Agent Stack
The Agent Stack by Vercel AI provides essential building blocks for creating production-grade agents, enabling seamless integration across multiple AI models and secure operations. It features components like AI Gateway for model routing, Workflow SDK for durable execution, and Vercel Connect for scoped access, streamlining agent development and deployment across various platforms.

