Vercel shipped ai@7.0.124 (speech/transcription telemetry) through ai@7.0.126 (clear tool approvals on addToolOutput) on 2026-09-30—22 commits since covered ai@7.0.123. Same day @ai-sdk/openai@3.0.123 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
- ✓ai@7.0.124 (17:48:28Z) → ai@7.0.126 (22:57:07Z); 22 commits since 7.0.123
- ✓Speech/transcription telemetry + provider usage + streaming lifecycle callbacks (
8c65988) - ✓Clear tool approvals when addToolOutput runs (
4f3d236); convertDataPart / multipart tool results in tree - ✓@ai-sdk/openai@3.0.123: serviceTier 'ultrafast' (docs: gpt-5.6-sol access-controlled)
- ✓
npm i ai@7.0.126 @ai-sdk/openai@3.0.123; https://ai-sdk.dev/docs/introduction
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
Speech/transcription lacked first-class telemetry; tool approvals could linger after addToolOutput; OpenAI ultrafast tier needed SDK exposure.
What shipped
ai@7.0.124–7.0.126 (22 commits since 7.0.123): speech telemetry; clear approvals on addToolOutput; @ai-sdk/openai@3.0.123 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 ai@7.0.126 @ai-sdk/openai@3.0.123. Docs: https://ai-sdk.dev/docs/introduction
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.