Skip to main content

Custom models

Image and video generation are currently unavailable when using models connected with your own API key (BYOK).
Qoder supports accessing third-party provider model resources via API keys.
Preset providers include: Alibaba Cloud Model Studio, DeepSeek, Z.ai, Kimi, MiniMax, Xiaomi MIMO, OpenAI, Google, and OpenRouterCustom providers: OpenAI Compatible and Anthropic Compatible
Special Note:Repo Wiki uses a fixed model and is billed separately. When generating, there will be a prompt notifying you of the additional credit consumption.

Adding Custom Models

1

Open Qoder Settings

Open Settings.
2

Open the Models panel

Select Models in the left navigation.
3

Add a model

Click Add model, then choose one of the following configuration methods:
  • For a preset provider: Select a provider and model, then enter your API key.
  • For a custom endpoint: Open Provider and select OpenAI Compatible or Anthropic Compatible under Custom.
    • For OpenAI Compatible, select Chat Completions API or Responses API.
    • Enter the Base URL, API key, and at least one Model ID. To configure more models for the same endpoint, click Add Model ID.
For a preset provider, click Get API key to open its key management page. For a custom provider, enter the exact Base URL supplied by the model service. Qoder displays https://api.example.com/v1 as an example format.
In an enterprise environment, a third-party provider may be labeled Direct connection or Cloud connection. Check the connection type when choosing the provider, then complete the configuration.
4

Configure model capabilities

Configure the options shown for your model based on the capabilities published by the model provider:
  • Display name: Set the name shown for the model in Qoder. The Model ID cannot be changed here.
  • Context window: Select one or more values supported by the model under Supported context windows, then choose a Default context window from those values.
  • Vision: Enable this capability if the model supports image input.
  • Thinking: Enable this capability if the model supports reasoning, then select its supported reasoning effort levels.
  • Maximum output tokens. When this option is available, enter a positive value within the range supported by the provider. It limits how many tokens the model can generate in one response.
5

Validate and add the model

Select Validate and add model. If you entered several model IDs for the same custom endpoint, Qoder checks each one. For a model-specific error, verify the indicated ID and your access to it. For an endpoint configuration error, check the Base URL, API key, and protocol. Run validation again after making changes. Qoder saves the configuration once validation succeeds.
6

Use the model

After configuration, select the configured model in the chat interface to start using it.

Managing Custom Models

In the "Models" panel, you can perform the following operations on custom models:
OperationDescription
EditUpdate the API key used by the model
DeleteRemove model, cannot be used after deletion

FAQ

1. Does using custom models consume Credits?

Custom model fees are billed directly to your provider API account and do not use Qoder Credits. However, Repo Wiki uses a fixed model and consumes Qoder Credits. A prompt appears when generating content.

2. How to obtain API keys?

Provider API key URLs:

3. What to do if adding a model fails?

Please check the following:
  1. Whether the Base URL is complete and the selected compatible protocol and API type match the endpoint
  2. Whether the API key is correct with no extra spaces, and has not expired or been disabled
  3. Whether the Model ID is correct and accessible to the provider account
  4. Whether the provider account has sufficient balance
  5. Whether the network connection is normal

4. Can I add multiple models from the same provider?

Yes. You can add different versions of models from the same provider or use different API keys.