How to Configure OpenAI Models with Continue

Discover OpenAI models here

Get an API key from the OpenAI Console

Configuration

YAML
JSON (Deprecated)

config.yaml

name: My Config
version: 0.0.1
schema: v1

models:
  - name: <MODEL_NAME>
    provider: openai
    model: <MODEL_ID>
    apiKey: <YOUR_OPENAI_API_KEY>

config.json

{
  "models": [
    {
      "title": "<MODEL_NAME>",
      "provider": "openai",
      "model": "<MODEL_ID>",
      "apiKey": "<YOUR_OPENAI_API_KEY>"
    }
  ]
}

Check out a more advanced configuration here

OpenAI API compatible providers

OpenAI API compatible providers include

If you are using an OpenAI API compatible providers, you can change the apiBase like this:

YAML
JSON (Deprecated)

config.yaml

name: My Config
version: 0.0.1
schema: v1

models:
  - name: <OPENAI_API_COMPATIBLE_PROVIDER_MODEL>
    provider: openai
    model: <MODEL_NAME>
    apiBase: http://localhost:8000/v1
    apiKey: <YOUR_CUSTOM_API_KEY>

config.json

{
  "models": [
    {
      "title": "<OPENAI_API_COMPATIBLE_PROVIDER_MODEL>",
      "provider": "openai",
      "model": "<MODEL_NAME>",
      "apiKey": "<YOUR_CUSTOM_API_KEY>",
      "apiBase": "http://localhost:8000/v1"
    }
  ]
}

How to Force Legacy Completions Endpoint Usage

To force usage of completions instead of chat/completions endpoint you can set:

YAML
JSON (Deprecated)

config.yaml

name: My Config
version: 0.0.1
schema: v1

models:
  - name: <OPENAI_API_COMPATIBLE_PROVIDER_MODEL>
    provider: openai
    model: <MODEL_NAME>>
    apiBase: http://localhost:8000/v1
    useLegacyCompletionsEndpoint: true

config.json

{
  "models": [
    {
      "title": "<OPENAI_API_COMPATIBLE_PROVIDER_MODEL>",
      "provider": "openai",
      "model": "<MODEL_NAME>",
      "apiBase": "http://localhost:8000/v1",
      "useLegacyCompletionsEndpoint": true
    }
  ]
}

How to Disable the Responses API

By default, Continue uses OpenAI’s /responses endpoint for o-series and gpt-5 models. If you encounter “organization must be verified” errors related to reasoning summaries or streaming, you can force the use of /chat/completions instead:

YAML
JSON (Deprecated)

config.yaml

name: My Config
version: 0.0.1
schema: v1

models:
  - name: gpt-5
    provider: openai
    model: gpt-5
    useResponsesApi: false

config.json

{
  "models": [
    {
      "title": "gpt-5",
      "provider": "openai",
      "model": "gpt-5",
      "useResponsesApi": false
    }
  ]
}

Getting Started

Features

Customize

Reference

Guides

Help

How to Configure OpenAI Models with Continue

Configuration

OpenAI API compatible providers

How to Force Legacy Completions Endpoint Usage

How to Disable the Responses API

​Configuration

​OpenAI API compatible providers

​How to Force Legacy Completions Endpoint Usage

​How to Disable the Responses API

Configuration

OpenAI API compatible providers

How to Force Legacy Completions Endpoint Usage

How to Disable the Responses API