Model Providers (BYOK)

Last updated · 2026-09-05

VibeSpace uses BYOK (Bring Your Own Key): you obtain an API key from the provider, paste it into the app, and you're set. Model requests go directly from your Mac to the provider — VibeSpace runs no relay, never sees your content, and takes no markup.

Supported providers

ProviderNotes
DeepSeekdeepseek-chat / deepseek-reasoner and more
GLM (Zhipu)glm-4 series
Kimi (Moonshot)kimi series
MiniMaxMiniMax series
Qwen (Alibaba)qwen series
Doubaodoubao series
OpenAIGPT series
AnthropicClaude series
GoogleGemini series
OpenRouteraggregator for many models
OpenAI-compatiblecustom base_url for any compatible service

Setup

  1. Open Settings → LLM Providers;
  2. Pick a provider and paste your API key;
  3. Click Test Connection to validate the key;
  4. Fetch models and choose a default (custom endpoints accept a manually typed model name);
  5. Optional: override the model's context window limit if auto-detection is wrong.

You can configure several providers at once and pick per task.

How your key is protected

  • Keys are encrypted with AES-256-GCM and stored separately from everyday config;
  • Decrypted only in memory while sending a request — never written to logs;
  • Keys go to the provider endpoint and nowhere else — not to VibeSpace's website or servers.

Network proxy

If a provider endpoint requires a proxy, go to Settings → System → Network:

  • Direct: default, connect straight to the provider;
  • System: follow macOS proxy settings;
  • Manual: enter a custom proxy address.

Usage tracking

Settings → Personal shows a token usage heatmap: day-by-day consumption to gauge cost and intensity per task.

Tip: context windows vary widely between models. For long tasks pick a large-window model and watch actual usage in the context panel.