OpenAI
API key, through the Responses API.
Models and connectors
Cloud APIs, subscriptions and engines that run inside the app all speak the same contracts. Pick a connector per session, and change it whenever you like.
Chat and agents
Images attach to prompts on every connector that accepts them.
API key, through the Responses API.
API key, through the Messages API.
Gemini API key.
Gemini and Claude models in your Google Cloud project.
Converse through a named AWS profile.
An AWS-hosted AgentCore harness session.
Any endpoint that serves Chat Completions: OpenRouter, Groq, DeepSeek, xAI, Kimi, MiniMax, Ollama, llama.cpp and more.
Apple Foundation Models on the Mac itself.
GGUF Qwen models run inside the app on the Tensor engine.
Subscriptions
Darkspyre runs on your existing Claude, ChatGPT and Gemini subscriptions as full agent sessions, held to the session's permission level.
Beyond text
| Kind | Connector | Runs |
|---|---|---|
| Image generation | ComfyUI workflows | Your ComfyUI server |
| Image generation | Supra | Inside the app |
| Speech synthesis | PocketTTS | Your PocketTTS server |
| Audio generation | TangoFlux | Your TangoFlux server |
| Speech transcription | Whisper (base.en to large-v3-turbo) | Inside the app |
Utility models
OpenAI and any OpenAI-compatible embedding endpoint.
Laya answers typed yes-or-no questions on ONNX Runtime inside the app. RightSize uses it to size work before it is dispatched.
Local engines
TensorSharp and ONNX Runtime are built into the app. Qwen text, Supra images, Whisper transcription and Laya decisions run in process, with nothing else to install.
Switching
Move a session from one model or provider to another at any point. Text, tool calls, tool results and attachments carry over. State that only one provider understands, such as signed reasoning, stays behind and is counted.
Agent sessions carry over too. Codex and Bedrock take the history as structured context. Claude, AgentCore and Antigravity receive a one-time transcript of the conversation so far.