Provider Catalog
The desktop app ships a catalog of 32 model providers. You connect each one in Settings -> Models by pasting an API key or, for the cloud providers, filling the credential form. Five of these providers are also native to the Wayland Core engine, which means the CLI can talk to them directly without the desktop. Everything else in the catalog routes through the engine using an OpenAI-compatible layer (ProviderCompat).
The provider id is the value the app stores internally and is the same id you use when you connect through the API. The group column matches the Browse grouping in the Models panel.
Engine-native providers
Section titled “Engine-native providers”These five work in both the desktop and the standalone wayland-core CLI. They have first-class auth paths in the engine.
| Provider | Id | Auth |
|---|---|---|
| Anthropic | anthropic | API key or OAuth (Claude.ai subscription) |
| OpenAI (and OpenAI-compatible) | openai | API key, optional base URL |
| Google Gemini | google-gemini | API key (native Generative Language API) |
| AWS Bedrock | aws-bedrock | AWS SigV4 (access key, profile, or environment) |
| Google Vertex AI | vertex | GCP OAuth2 or service account |
Local models reach the engine through the OpenAI-compatible path. See Use a Local Model.
Full desktop catalog
Section titled “Full desktop catalog”All 32 providers, in the catalog’s render order. The five engine-native providers are marked.
| Provider | Id | Group | Engine-native |
|---|---|---|---|
| Anthropic | anthropic | Frontier | Yes |
| OpenAI | openai | Frontier | Yes |
| Google Gemini | google-gemini | Frontier | Yes |
| AWS Bedrock | aws-bedrock | Cloud | Yes |
| Google Vertex AI | vertex | Cloud | Yes |
| OpenRouter | openrouter | Open | No |
| Groq | groq | Open | No |
| xAI Grok | xai | Frontier | No |
| Mistral | mistral | Frontier | No |
| Cohere | cohere | Frontier | No |
| Perplexity | perplexity | Open | No |
| Together AI | together | Open | No |
| Fireworks AI | fireworks | Open | No |
| Cerebras | cerebras | Open | No |
| Replicate | replicate | Open | No |
| Hugging Face | huggingface | Open | No |
| NVIDIA NIM | nvidia | Open | No |
| Anyscale | anyscale | Open | No |
| DeepSeek | deepseek | Chinese | No |
| Moonshot | moonshot | Chinese | No |
| Qwen | qwen | Chinese | No |
| Baichuan | baichuan | Chinese | No |
| Yi | lingyiwanwu | Chinese | No |
| Zhipu GLM | zhipu-glm | Chinese | No |
| MiniMax | minimax | Chinese | No |
| Stability AI | stability | Open | No |
| Deepgram | deepgram | Voice | No |
| AssemblyAI | assemblyai | Voice | No |
| ElevenLabs | elevenlabs | Voice | No |
| Azure OpenAI | azure | Cloud | No |
| Flux Router | flux-router | Open | No |
| OpenAI-compatible | openai-compatible | Open | No |
Notes on groups
Section titled “Notes on groups”- Frontier and Open providers connect with a single API key. The app recognizes most keys by their prefix and selects the right provider for you.
- Cloud providers (AWS Bedrock, Google Vertex AI, Azure OpenAI) use a multi-field credential form rather than a single key.
- Voice providers (Deepgram, AssemblyAI, ElevenLabs) power speech-to-text and text-to-speech. See Set Up Voice.
- Stability AI and Flux Router are the providers most often paired with image generation. See Set Up Image Generation.
- OpenAI-compatible is the entry to use for any server that speaks the OpenAI API, including a local Ollama or vLLM endpoint.