Official TypeScript SDK [email protected] (v7.25.0, 2026-09-29) adds Computer Use to beta.agents (#2837), mirroring Python 3.22.0. Prior v7.24.0 shipped Agents credential/session options (#2812), the gpt-6.1-sol model id (#2836), Responses Cyber access, Realtime Translation client secrets, and a dedicated Node translation WebSocket. 35 commits ahead of v7.23.0.

Key Takeaways

  • ✓Releases v7.24.0 → v7.25.0; npm [email protected]; 35 commits ahead of v7.23.0
  • ✓Computer Use on beta.agents via #2837
  • ✓gpt-6.1-sol id (#2836); Agents credential/session options (#2812)
  • ✓Realtime Translation client secret (#2819) + Node translation WebSocket (#2818)
  • ✓Upgrade: npm i [email protected]; docs: platform.openai.com agents + API reference
OpenAI Node 7.25.0: Computer Use on beta.agents; 7.24 adds GPT-6.1 Sol + Agents credential/session options
🖼️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

TS Agents lagged Python on Computer Use bindings, GPT-6.1 Sol ids, and session/credential helpers. openai-node 7.24–7.25 close that gap for cross-language stacks.

What shipped

v7.25.0: Computer Use on beta.agents (#2837). v7.24.0: Agents credential/session (#2812), gpt-6.1-sol (#2836), Cyber access, Realtime Translation secret + Node WS. 35 commits ahead of v7.23.0.

Benchmarks

No official Computer Use latency/SWE numbers. Anchors: npm 7.25.0; compare ahead_by

  1. Measure your own environment round-trips.

Get started

npm i [email protected]; use beta.agents + environments/sessions; pin gpt-6.1-sol when needed. Docs: https://platform.openai.com/docs/guides/agents

Action HubReady to adopt this in production?

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

Up NextCline 4.1.22: GPT-6.1 Sol becomes default across gateways; Anthropic server-side refusal fallback; Bee & Pareto providers
Read Now→