Connect your application to the inference gateway

Start with the right application context

Stimulir offers OpenAI-compatible chat completions at https://api.stimulir.com/api/v1/inference/chat/completions. Authenticate with a workspace API key beginning with hyb_. Your Console sign-in session and your application API key serve different purposes. Keep your key in your application's environment. Do not put real credentials into support messages, screenshots, source control, or browser code.

Send a request

Choose a model listed for your workspace. Use the standard messages array for the system prompt and conversation history. Model routing uses your matching BYOK credential or managed inference as described in the developer reference. For the endpoint and request examples, read the Inference API reference. For creating an application key, read API keys.

If a request fails

• Check that the request uses the gateway URL and an application API key for the intended workspace.
• Check the requested model and any project attribution against your workspace configuration.
• Preserve the error code and trace ID for troubleshooting. Share those identifiers rather than a credential.

If you need help, sign in to Console and open support. Include your environment and Console version so the team can check the relevant release.