Models, Providers, and Profiles

A provider is a service that runs models, and a model is the specific one the agent thinks with. Wayland separates the two: you connect a provider once with credentials, then choose among its models. Different assistants and conversations can use different models, so you can pair a strong reasoning model where it matters with a faster one elsewhere.

The catalog and engine-native routing

The desktop catalog lists 34 providers, from Anthropic and OpenAI to OpenRouter, Groq, Mistral, NVIDIA NIM, Moonshot, Sakana AI (Fugu), and local and regional services. A core set is engine-native, meaning the engine speaks to their APIs directly: Anthropic, OpenAI and its compatibles, Google Gemini, AWS Bedrock, and Google Vertex AI. The OpenAI-compatible path is wide: it covers DeepSeek, Ollama, and other services that present an OpenAI-shaped API. The broader desktop catalog builds on these plus additional integrations.

The redesigned provider picker leads with real brand logos and a bring-your-own-endpoint section up front, and covers the full engine catalog of 104 providers. More providers now route natively through the engine, including xAI Grok, Perplexity, OpenRouter, Groq, DeepSeek, Cerebras, and NVIDIA, for cleaner, more reliable connections. The chat header and send box read friendly model names such as Claude Opus 4.8 rather than a raw model id, and the connected providers list shows real brand logos.

ProviderCompat

Each provider has quirks: a different field name for the token limit, different rules about merging messages, schema sanitization for Bedrock. The engine handles these through a ProviderCompat layer, which is configuration rather than hardcoded branches. Each provider type has sensible defaults, and you can override any field. Adding or adjusting a provider is a config change, not a code change, which is what keeps the catalog wide.

Credentials

You add a cloud provider by entering its credentials in the Models settings, where the desktop also offers one-click and JSON import for getting keys in quickly. The engine reads credentials from its config file and from environment variables, with flags able to override per run. See Add a Cloud Model Provider and Use a Local Model.

Profiles

A profile is a named bundle of provider and model settings you can switch to as a unit. Profiles support an extends field, so one profile can inherit from another and change only what differs. A profile for a fast local model and a profile for a frontier cloud model can each be a one-flag switch. On the command line, --profile selects one; the desktop offers the same model selection per conversation.

Next

• Add a Cloud Model Provider
• Use a Local Model (Ollama)
• Architecture Overview