Update models document page to cover gpt-5 #364
Conversation
|
| name: 'My Agent', | ||
| instructions: "You're a helpful agent.", | ||
| modelSettings: { | ||
| reasoning: { effort: 'minimal' }, |
There was a problem hiding this comment.
I think we should also encourage people to try out medium and high. Just always optimizing for latency doesn't seem like an ideal recommendation. We already dumb down the model with low to make the latency closer to what people expect from non-reasoning models. However, just because that's the fastest and an okay default doesn't mean it's what people should strive for.
| | `truncation` | `'auto' \| 'disabled'` | Token truncation strategy. | | ||
| | `maxTokens` | `number` | Maximum tokens in the response. | | ||
| | `store` | `boolean` | Persist the response for retrieval / RAG workflows. | | ||
| | `reasoning.effort` | `'minimal' \| 'low' \| 'medium' \| 'high'` | Reasoning effort for gpt-5 etc. | |
There was a problem hiding this comment.
In your other code samples from other PRs these were still under providerDetails. If they are top level I think that's better. Just calling it out.
Also GPT-5 should be capitalized in here
This document update needs to be merged after releasing #363 changes.