NextChat - ScitiX

NextChat is a lightweight, cross-platform ChatGPT-style web/desktop client. It overrides the OpenAI base URL through environment variables, so you can point it to the ScitiX Model Inference API and use ScitiX models. Supported models include glm-5.2 and DeepSeek-V4-Flash. For model pricing, see the model catalog.

Configure

Create an API Key on the API Keys page. NextChat reads its OpenAI connection from environment variables. Set these before starting:

export OPENAI_API_KEY="<Your API Key>"
export BASE_URL="https://api.scitix.ai/model-api"
export CUSTOM_MODELS="-all,+glm-5.2,+DeepSeek-V4-Flash"

Variable	Description
`OPENAI_API_KEY`	Your API Key created on the API Keys page.
`BASE_URL`	ScitiX endpoint without the `/v1` suffix: `https://api.scitix.ai/model-api`. NextChat appends `/v1/chat/completions` itself.
`CUSTOM_MODELS`	`-all` hides the default models; `+glm-5.2,+DeepSeek-V4-Flash` adds the ScitiX models to the picker.

BASE_URL must not include /v1, or NextChat will duplicate the path when it appends /v1/chat/completions.

Choose a model with native tool calling if you use plugin or tool features. The same three variables apply when deploying on Vercel. Set them in the project’s environment variables. For Docker, pass them with -e OPENAI_API_KEY=... -e BASE_URL=... -e CUSTOM_MODELS=....

Verify

Open NextChat, pick a ScitiX model from the selector, and send a message. A normal reply confirms that the connection works.

NextChat — chatting with a ScitiX model

FAQ

Model picker empty or defaults showing: check CUSTOM_MODELS. -all clears the built-in list, then +<model> adds each ScitiX model.