https://retellai.com/?utm_source=discord&utm_medium=seo logo
how do i get gpt 4o via api as opposed to using gp...
# ❓・ai-evy-support
b
@AI Evy how do i get gpt 4o via api as opposed to using gpt 4.1?
a
Thanks for tagging me @breeshwayne. I'll look through relevant sources and get back to you shortly.
[(3) ]() When calling the create or update LLM endpoints, you would set the
model
parameter to your desired model. Note that the official documentation lists the currently available model options as:
gpt-4.1
,
gpt-4.1-mini
,
gpt-4.1-nano
,
gpt-5
,
gpt-5.1
,
gpt-5.2
,
gpt-5-mini
,
gpt-5-nano
,
claude-4.5-sonnet
,
claude-4.5-haiku
,
gemini-2.5-flash
,
gemini-2.5-flash-lite
,
gemini-3.0-flash
. [(4) ]() [(5) ]() However, based on community feedback, GPT-4o remains accessible via the API even though it's not listed in the current documentation options. [(1) ]() [(2) ]() Be aware that Azure plans to deprecate GPT-4o around February 2026, so it may eventually be fully removed. [(1) ]() [(2) ]()
### Answer GPT-4o has been deprecated from the Retell AI dashboard UI but can still be used via the API. [(1) ]() [(2) ]() To use GPT-4o, you'll need to specify it when creating or updating your Retell LLM through the API. The
model
field accepts the model name as a string value. [(3) ]() [(4) ]() [(5) ]() Here's an example using the JavaScript SDK to create an LLM with a specific model:
Copy code
javascript
import Retell from 'retell-sdk';
const client = new Retell({
  apiKey: 'YOUR_RETELL_API_KEY',
}) ;
​ To learn more, see the sources I considered: [[1] Urgent: GPT-4o Model Clarification :](https://discord.com/channels/1186424376300679209/1438933812204671148) [[2] gpt 4o switching to 4.1 automatically](https://discord.com/channels/1186424376300679209/1437572068215623700) [[3] Get Retell LLM](https://docs.retellai.com/api-references/get-retell-llm) [[4] Create Retell LLM](https://docs.retellai.com/api-references/create-retell-llm) [[5] Update Retell LLM](https://docs.retellai.com/api-references/update-retell-llm) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.