⚡

Developer 3s Key Decision Metrics

TL;DR Verdict
🏆 Benchmark Rank72s 必看
Top Tier Benchmark
Full Leaderboard→
💰 Cost & Plans比价
Model id gpt-6.1-sol; specs $2
Compare Plans↗
🛠️ Ecosystem & IDERules
Vercel AI SDK
Setup IDE Rules↗

Vercel AI SDK shipped @ai-sdk/[email protected] and @ai-sdk/[email protected] on 2026-09-30, adding native GPT-6.1 Sol (gpt-6.1-sol) support on the v5/v6 provider lines (#21747, backport #21749). Official pricing: $2/$10 per 1M tokens (cached input $0.10), 1.05M context, 128k max output.

Key Takeaways

  • ✓Shipped @ai-sdk/[email protected] and @2.0.132 with GPT-6.1 Sol (#21747 / #21749)
  • ✓Model id gpt-6.1-sol; specs $2/$10 per 1M, cached input $0.10, 1.05M context, 128k max out
  • ✓Mid-tier coding/computer-use path vs Astra; aligns with Codex defaulting to Sol
  • ✓Upgrade: npm i @ai-sdk/[email protected] (or 2.0.132 on v5 line)
  • ✓Docs: OpenAI provider
🧭

Finished reading? Explore benchmark rankings & pricing

Real-world SWE-bench scores & $20/mo vs API cost break-even calculator

🏆 Leaderboard→💰 Compare Plans↗
🔗

Project Links & Resources

Direct Access
Direct access to official project resources and documentation
🐙
@ai-sdk/[email protected] release
github.com/vercel/ai/releases/tag/%40ai-sdk/openai%403.0.121
↗
🐙
@ai-sdk/[email protected] release
github.com/vercel/ai/releases/tag/%40ai-sdk/openai%402.0.132
↗
🐙
PR #21747 GPT-6.1 Sol support
github.com/vercel/ai/pull/21747
↗
📖
GPT-6.1 Sol model card
developers.openai.com/api/docs/models/gpt-6.1-sol
↗
📖
AI SDK OpenAI provider docs
ai-sdk.dev/providers/ai-sdk-providers/openai
↗
📖
npm @ai-sdk/openai 3.0.121
www.npmjs.com/package/@ai-sdk/openai/v/3.0.121
↗
🐙
#21749
github.com/vercel/ai/pull/21749
↗
🐙
4972874
github.com/vercel/ai/commit/4972874a2c416f08a92440beedd8e57e92dda062
↗
🔬

In-Depth Technical Analysis

Background After GPT-6.1 Sol became OpenAI’s mid-tier coding/computer-use default candidate (and Codex 0.159.1 defaulted to it), AI SDK apps needed first-class provider support instead of opaque model strings. ### What shipped @ai-sdk/[email protected] and @2.0.132 register GPT-6.1 Sol (#21747 / #21749). Docs: OpenAI provider. ### Benchmarks No SWE-bench in the SDK notes. Official model specs: $2/$10 per 1M, cached input $0.10, 1.05M context, 128k max out. Validate Astra vs Sol on your tasks. ### Get started npm i @ai-sdk/[email protected] (or 2.0.132 on the v5 line); set model: 'gpt-6.1-sol'.