GPT-6.2 Astra and Sol now available on Vercel AI Gateway
OpenAI's GPT-6.2 Astra and GPT-6.2 Sol models are now available on Vercel AI Gateway, using model IDs openai/gpt-6.2-astra and openai/gpt-6.2-sol. Both models support the Responses API and an Ultrafast service tier for lower latency at higher per-token rates; GPT-6.2 Astra's Ultrafast output-token price is stated as 60% lower than GPT-6 Astra's.

Why it matters
Builders using Vercel AI Gateway can call the new models by model ID, including through the AI SDK and Chat Completions or Responses APIs. The Ultrafast tier trades higher per-token cost for lower latency, which affects latency-sensitive features and cost planning.
Who should care
Developers building AI features on Vercel, teams using AI SDK or coding agents such as Codex and Cursor, and anyone choosing models for latency or cost trade-offs.
What you can do
Set your AI Gateway API key and try openai/gpt-6.2-sol or openai/gpt-6.2-astra in the playground or your API calls, then compare latency and cost with the Ultrafast tier enabled.