Vercel shipped [email protected] (speech/transcription telemetry) through [email protected] (clear tool approvals on addToolOutput) on 2026-09-30—22 commits since covered [email protected]. Same day @ai-sdk/[email protected] adds OpenAI serviceTier: 'ultrafast' (docs: access-controlled, gpt-5.6-sol), plus Azure MAI speech/transcribe and MCP OAuth conditional invalidation patches in the tree.

Key Takeaways

Vercel AI SDK: ai@7.0.124–7.0.126 speech telemetry + tool-approval clear; @ai-sdk/openai ultrafast service tier
🖼️Official Media
Click to view high-res
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

🔬

In-Depth Technical Analysis

Background

Speech/transcription lacked first-class telemetry; tool approvals could linger after addToolOutput; OpenAI ultrafast tier needed SDK exposure.

What shipped

[email protected]–7.0.126 (22 commits since 7.0.123): speech telemetry; clear approvals on addToolOutput; @ai-sdk/[email protected] adds serviceTier ultrafast (gpt-5.6-sol access-controlled per docs).

Benchmarks

No official TTFT/SWE numbers. Anchors: 7.0.124 17:48:28Z; 7.0.126 22:57:07Z.

Get started

npm i [email protected] @ai-sdk/[email protected]. Docs: https://ai-sdk.dev/docs/introduction

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

Up NextVercel AI SDK @ai-sdk/openai 4.0.78: GPT-6 Sol/Luna allow reasoningEffortUpdate 'none'
Read Now→