My automated tasks with image generation stopped working with the gpt5 update. Is this feature still supported?
#Automated tasks
vast locust
tribal jayBOT
Hi @vast locust. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Short answer: Yes—image generation is still supported, but how you access it may have changed with GPT‑5.
-
In ChatGPT: GPT‑5 supports image generation among its tools, though “GPT‑5 Pro” specifically does not include image generation (use standard GPT‑5 or enable 4o Image Generation in GPTs) (Tools support in ChatGPT, GPT‑5 in ChatGPT, 4o Image Generation in GPTs, Creating images in ChatGPT FAQ).
-
In the API: Image generation is handled by the GPT Image model (gpt-image-1). For multi‑turn or chat flows, use the Responses API with the image_generation tool; for single-shot generations/edits, use the Images API. Supported “mainline” models for tool-calling include gpt‑4o/4.1/o3; documentation examples also show usage with GPT‑5 as the orchestrating model, but the image generation itself runs through gpt‑image‑1 (Image generation guide, Tools: image generation, Supported models for tool-calling, Multi‑turn examples).
If your automations broke after the GPT‑5 switch:
- Ensure you’re not using GPT‑5 Pro for image generation in ChatGPT (it’s not supported) (GPT‑5 in ChatGPT).
- For API workflows, continue calling gpt-image-1 via the Images API, or include the image_generation tool when using Responses. If you were relying on a playground feature like streaming previews, note that a recent incident showed “Streaming is not supported” for images; this was resolved, but streaming isn’t generally supported on the Images API request itself (Forum incident).
If you share your current API call (endpoint/model/params), I can point to the minimal change needed.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
vast locust
----------------------
Short answer: Yes—image generation is still supported, bu...
You didn't mention anything about the automated tasks feature in ChatGPT
sacred matrix
@tribal jay is the automated tasks feature supported with gpt 5?
tribal jayBOT
Let me check the knowledge base for you again. One moment! :books:
Yes, automated tasks—including image generation—are supported with GPT-5. The knowledge sources confirm that GPT-5 supports every tool available in ChatGPT, including image generation, web search, data analysis, and more. This means you can use GPT-5 for automated workflows that involve these features, as long as you are not using the "GPT-5 Pro" mode, which does not support image generation or Canvas (Tools Support in ChatGPT, GPT-5 in ChatGPT).
For API-based automation, you can use GPT-5 as the orchestrating model with the Responses API and include the image_generation tool in your requests. The actual image generation is performed by the gpt-image-1 model, but GPT-5 can reliably call this tool as part of automated tasks (Image generation guide, Tools: image generation).