Is it possible to choose the Responses API or OpenAI ?
It has been updated a few months ago by OpenAI, but the node still seems to be using the old Completions API. [https://platform.openai.com/docs/guides/migrate-to-responses\]
I tried to restrict my API key to only the Responses API, to see if the call would pass. it did not.
I also tried modifying the endpoint of the credential, I guess it is not the place to do it.
Why aren’t those major important nodes aren’t being updated on the same day of an update ?
The Gemini one too is getting old (with the use of PALM ← depreciated]
So this is a feature request to update your major nodes,.
It there an easy way to chose the endpoint on the user side ?
What’s the point to use n8n, if I need to code the API calls to get the up to date versions?
Responses benefits
The Responses API contains several benefits over Chat Completions:
Better performance: Using reasoning models, like GPT-5, with Responses will result in better model intelligence when compared to Chat Completions. Our internal evals reveal a 3% improvement in SWE-bench with same prompt and setup.
Agentic by default: The Responses API is an agentic loop, allowing the model to call multiple tools, like
web_search,image_generation,file_search,code_interpreter, remote MCP servers, as well as your own custom functions, within the span of one API request.Lower costs: Results in lower costs due to improved cache utilization (40% to 80% improvement when compared to Chat Completions in internal tests).
Stateful context: Use
store: trueto maintain state from turn to turn, preserving reasoning and tool context from turn-to-turn.Flexible inputs: Pass a string with input or a list of messages; use instructions for system-level guidance.
Encrypted reasoning: Opt-out of statefulness while still benefiting from advanced reasoning.
Future-proof: Future-proofed for upcoming models.
