# GPT-6 Astra API Brings Computer Use to Developers _GPT-6 Astra adds computer use with background control plus async tools and steering, now available in ChatGPT, Codex and the API._ **Updated:** 2026-10-28 **Published:** 2026-09-04 **Source:** https://www.startuphub.ai/ai-news/technology/2026/gpt-6-astra-api-brings-computer-use-to-developers --- [GPT-6 Astra API](https://www.youtube.com/watch?v=bOC3DisEOfg) is OpenAI's newest frontier model, shown off with the ability to control a desktop directly. According to [OpenAI's YouTube channel](https://www.youtube.com/watch?v=bOC3DisEOfg), the upgrade arrives in [ChatGPT](https://www.startuphub.ai/ai-news/artificial-intelligence/2026/openai-s-chatgpt-gains-context-with-computer-history-feature), Codex and the API. Users only need a prompt or an authenticated API call, no remote exploitation required. The full discussion can be found on **OpenAI Youtube**'s YouTube channel. ![Introducing GPT-6 Astra for developers - OpenAI Youtube](https://img.youtube.com/vi/bOC3DisEOfg/maxresdefault.jpg) Introducing GPT-6 Astra for developers, from OpenAI Youtube That distinction matters for security. ## How computer control actually works In the demo, Astra paints in Krita from a photo prompt, adding the Golden Gate Bridge in Van Gogh style while watching screenshots. It keeps the app running in the background so the user can keep working. Think of it like a remote intern with screen sharing and mouse access, but with no lock on the filing cabinet. OpenAI says Astra tracks the original instruction across app controls and applies the same ability to everyday developer workflows, from filling forms for API keys to QA on a mobile app. Two new Responses API primitives extend that autonomy. Asynchronous tool calling lets the model continue work while a tool runs and absorb the result when it returns. Steering lets you inject new context mid-response without canceling the running tool, as shown in the [Codex](https://www.startuphub.ai/ai-news/artificial-intelligence/2026/codex-it-s-time-to-fly)-style live redirect. ### How to use GPT-6 Astra GPT-6 Astra is available in three places, ChatGPT, Codex and the API. In ChatGPT it is offered in ChatGPT Work. OpenAI said computer use is easiest to see in the ChatGPT app. For business accounts, Astra is off by default at launch. An administrator must enable it and set which websites, desktop apps and uploads it may use and when it must ask for confirmation. In Codex, OpenAI gave Astra a photo to paint in Krita in the style of Van Gogh with the Golden Gate Bridge behind it. Astra worked the app through screenshots while the app stayed in the background, so the user could keep working. In the API, Astra works through the Responses API, which adds asynchronous tool calling to keep working while a tool runs and steering to add instructions mid-response without cancelling. [API pricing](https://www.startuphub.ai/ai-news/artificial-intelligence/2026/gpt-6-astra-is-powerful-pricey-and-still-gated) is $10 per million input tokens and $50 per million output tokens. Prompts over 272K inputs cost 2x input and 1.5x output for the request, and Fast mode is 2x price for 2x speed. Tool calls for search and computer use cost per call, and Astra has a 1,050,000 token window with 128,000 tokens of output. For lighter work the [Sol and Luna](https://www.startuphub.ai/ai-news/artificial-intelligence/2026/openai-halves-sol-and-luna-pricing-after-astra) tiers are cheaper and faster. ## Why this matters and what is not fixed For builders, accuracy and efficiency gains in computer use lower friction for agent automation. They also widen the surface where a misinterpreted instruction or injected prompt can drive clicks, form fills and file edits. OpenAI did not detail permissions, sandboxing or audit logging for background control in this video. There is no mention of mitigations for prompt injection in the browser, tool output handling or limits on unattended actions. Teams should treat Astra-driven desktop sessions as privileged. Scope it to isolated VMs, require explicit approval for writes, and log every screenshot-driven action and async tool result. The steering change also creates timing risk. A mid-flight instruction can now alter a plan while a prior tool is still executing, so validate new context against the original task before the model merges it. OpenAI positions Astra as stronger on creativity and long-running tasks, with more detailed 3D models and more natural back and forth. That helps for knowledge work, but it does not answer how reliably it refuses destructive or out-of-scope computer actions. Astra is now available in ChatGPT, Codex and the API for testing on complex tasks. --- Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory. © StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training on this content requires a license. See https://www.startuphub.ai/terms.