AI Gateway: GPT
By Steven Van ·
On AI Gateway, GPT-5.6 Luna and GPT-5.6 Terra are now cheaper and GPT-5.6 Sol is faster.
On Vercel's AI Gateway, GPT-5.6 Luna and GPT-5.6 Terra are cheaper and GPT-5.6 Sol runs faster in fast mode. Since AI Gateway adds no markup on token pricing, the changes reach developers at the upstream rate, for both short and long context.
- openai/gpt-5.6-luna: 80% price reduction, to $0.2 per 1M input tokens and $1.2 per 1M output tokens (short context).
- openai/gpt-5.6-terra: 20% price reduction, to $2 per 1M input tokens and $12 per 1M output tokens (short context).
- openai/gpt-5.6-sol: price unchanged, but fast mode is now 2.5x faster, up from 1.5x.
Model IDs haven't changed, so existing requests pick up the new rates and speed without any code changes.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →