Providers
Set up OpenAI
Connect an OpenAI project key, sync the models available to that project, and use the Responses wire in Kition.
Updated
By Kition Docs
Verified against Kition 0.1.41 (d3e1b931) on 2026-08-29
Before you connect
Create or choose an OpenAI project and issue an API key for that project. Provider access, billing, model availability, and rate limits are controlled by OpenAI rather than by your Kition plan.
Use a dedicated key with the smallest practical scope and provider-side spend controls. Do not reuse an organization-wide credential when a project key will do.
Connect OpenAI
- Open Settings → AI Providers and select OpenAI
- Paste the API key into the API key field
- Leave the models endpoint as
/modelsunless OpenAI documents a different path for your account or gateway - Choose Sync now to fetch models, enable OpenAI, and make it the active provider
- Open the Agent model picker and choose a text-generation model returned for your project
Note
Save Provider stores edits, but a successful Sync now is what enables the provider, records its model catalog, and makes it active in Kition 0.1.41.
Connection used by Kition
Kition 0.1.41 uses the OpenAI Responses wire for Agent generation. It does not fall back to legacy Chat Completions when a Responses request is unsupported.
Base URL: https://api.openai.com/v1
Models endpoint: /models
Wire API: responses
Authentication: Bearer API keyChoose a model from the synced catalog
Do not copy a model ID from an old guide. Sync the catalog for the connected project and select a current text-generation model that your account can use.
The OpenAI models endpoint can return models for several modalities and API surfaces. If the first automatically selected entry is not suitable for Agent text work, change it in the Agent model picker before sending a task.
Credential storage in 0.1.41
Kition stores the key outside the workspace in its local application-data secrets directory. In this release those secret files are plaintext and are not protected by the operating-system keychain.
Heads up
Protect the operating-system account and disk, exclude Kition application data from shared backups, and revoke the key in OpenAI immediately if the device or key may be compromised.
Troubleshoot safely
401or403— verify the key, project access, and provider permissions404during model sync — restore the built-in Base URL and/modelspath; do not substitute/chat/completions429— review the current project quota, rate limits, and billing state in OpenAI- A model appears but generation fails — confirm that the selected model supports the Responses API and the requested tools
- Unexpected usage — disable OpenAI in Kition, revoke the remote key, review provider usage, and issue a replacement; do not rely on Disconnect to erase the local secret in 0.1.41
Implementation sources
Related pages
Set up Anthropic
Connect an Anthropic API key, sync the models available to its workspace, and use the Messages wire in Kition.
Switch the active provider and model
Understand the device-wide model selection that Kition 0.1.41 saves when you sync a provider or use the Agent model picker.
Protect provider credentials
Understand how Kition 0.1.41 stores provider secrets and reduce the impact of device or key compromise.