Skip to main content
BRICKS Project Desktop supports multiple AI model providers. Configure API keys in settings to enable a provider.

​
Anthropic

ModelReasoningExtended thinking
claude-sonnet-4.6Yes—
claude-opus-4.6YesMax
claude-haiku-4-5-20251001Yes—

​
OpenAI

ModelReasoningExtended thinking
gpt-5.4YesMax
gpt-5.3-codexYesMax
gpt-5.2-codexYesMax
gpt-5.2YesMax
gpt-5.1-codex-miniYes—

​
OpenAI Codex

ModelReasoningExtended thinking
gpt-5.4YesMax
gpt-5.4-miniYesMax
gpt-5.3-codexYesMax
gpt-5.2-codexYesMax

​
Google

ModelReasoningExtended thinking
gemini-3-flash-previewYes—
gemini-3-pro-previewYes—

​
GitHub Copilot

ModelReasoningExtended thinking
claude-sonnet-4.6Yes—
claude-opus-4.6YesMax
claude-haiku-4-5-20251001Yes—
gpt-5.4YesMax
gpt-5.4-miniYesMax
gpt-5.3-codexYesMax
gpt-5.2YesMax
gpt-5.2-codexYesMax
gemini-3.1-proYes—
gemini-3-proYes—
gemini-3-flashYes—
grok-code-fast-1——
GitHub Copilot uses OAuth for authentication. Configure it in Settings > Providers > GitHub Copilot. OpenAI Codex uses OAuth for authentication (Login with OpenAI). Configure it in Settings > Providers > OpenAI Codex.

​
OpenAI Compatible endpoints

Add any number of OpenAI-compatible API endpoints, each with its own name, base URL, API key, and model list. Manage endpoints in Settings > OpenAI Compatible Endpoints. Each endpoint is configured with:
FieldDescription
Endpoint NameA display name (e.g., “Ollama”, “vLLM”, “LM Studio”)
Base URLThe API endpoint (e.g., http://localhost:11434/v1)
API KeyOptional, depending on the provider
ModelsOne or more model identifiers available at this endpoint
Models from configured endpoints appear in the model selector grouped under the endpoint name. This allows you to use local models (Ollama, LM Studio) or any third-party provider that implements the OpenAI API format.
If you previously configured a single OpenAI Compatible provider, it is automatically migrated to the new multi-endpoint format on first launch.

​
Thinking levels

Models with reasoning support can use different thinking levels to control the depth of analysis:
LevelToken budgetBest for
Off—Fast responses, simple tasks
High~16k tokensMost tasks
Max~32k tokensComplex reasoning, architecture decisions
The Max level is only available on models marked with “Max” in the extended thinking column above.

​
Environment variable fallback

If no API key is configured in the app settings, the agent checks these environment variables:
  • ANTHROPIC_API_KEY — used for Anthropic models
  • OPENAI_API_KEY — used for OpenAI models