Vercel AI SDK shipped @ai-sdk/[email protected] on 2026-09-26: request-level and positioned system-message reasoningEffortUpdate now accept 'none' so GPT-6 Sol/Luna conversations can turn reasoning off mid-thread. Updates are validated against each model’s supported efforts—unsupported request-level updates warn and omit; unsupported historical/message-level updates reject. Companion @ai-sdk/[email protected] and @ai-sdk/[email protected] pick up the dependency.

Key Takeaways

  • ✓Shipped: @ai-sdk/[email protected] / npm 4.0.78
  • ✓Feature: reasoningEffortUpdate 'none' for GPT-6 Sol/Luna (#21518)
  • ✓Validation: warn+omit unsupported request-level; reject unsupported historical updates
  • ✓Companions: Azure 4.0.82, Bedrock 5.0.97; see OpenAI provider docs
  • ✓Install: npm i @ai-sdk/[email protected]
Vercel AI SDK @ai-sdk/openai 4.0.78: GPT-6 Sol/Luna allow reasoningEffortUpdate 'none'
🖼️Official Media
Click to view high-res
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
See how it ranks on the leaderboard
Full Leaderboard→
💰 Cost & PlansCompare
in: $2 / out: $10
Compare Plans↗
🛠️ Ecosystem & IDERules
Vercel AI SDK · @ai-sdk/openai · reasoningEffortUpdate
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

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

⚔️ Compare Model→💰 Compare plans & limits↗
🔗

Project Links & Resources

Direct Access
Direct access to official project resources and documentation
🐙
GitHub Release @ai-sdk/[email protected]
github.com/vercel/ai/releases/tag/%40ai-sdk/openai%404.0.78
↗
📖
npm @ai-sdk/openai 4.0.78
www.npmjs.com/package/@ai-sdk/openai/v/4.0.78
↗
🐙
Commit 94d5d6d allow none in reasoning effort updates
github.com/vercel/ai/commit/94d5d6d3e607f5cdaf112ca8674a86f1da03f8b7
↗
📖
AI SDK OpenAI provider options
ai-sdk.dev/providers/ai-sdk-providers/openai#provider-options
↗
🐙
GitHub Release @ai-sdk/[email protected]
github.com/vercel/ai/releases/tag/%40ai-sdk/azure%404.0.82
↗
🐙
vercel/ai repository
github.com/vercel/ai
↗
🐙
@ai-sdk/[email protected]
github.com/vercel/ai/releases/tag/%40ai-sdk/amazon-bedrock%405.0.97
↗
🐙
#21418
github.com/vercel/ai/pull/21418
↗
🔬

In-Depth Technical Analysis

Core Background & Industry Pain Points

GPT-6 Sol/Luna can set reasoning effort to none mid-conversation while preserving the prompt-cache prefix. The SDK previously rejected 'none' in reasoningEffortUpdate, so apps could not turn reasoning off after earlier turns used it.

Architecture Highlights & Internals

@ai-sdk/[email protected] (94d5d6d) allows 'none' for request-level and positioned system-message updates, validates against each model’s supported efforts (warn+omit vs reject), and ships with Azure 4.0.82 / Bedrock 5.0.97 dependency bumps. Builds on message-level updates from #21418.

Authoritative Benchmarks & Measured Scores

No latency/cost benchmarks published; PR notes live provider acceptance was not run. Measure reasoning-token and bill deltas for low→none on a fixed multi-turn script while confirming cache prefixes stay intact.

Developer Hands-on Guide

npm i @ai-sdk/[email protected]; set providerOptions.openai.reasoningEffortUpdate: 'none' per OpenAI provider options. npm: 4.0.78.

Action HubReady to adopt this in production?

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

⚔️ Launch VS Compare→💳 View Plans↗
Up NextCodex CLI 0.157.0: GPT-6 Sol/Luna (incl. Bedrock), fullscreen transcript + background daemon by default
Read Now→