Recently Supported
Qwen3.5 Small 0.8B-9B native multimodal w/ more intelligence, less compute
gpt-realtime-1.5 by OpenAI Tighter instruction adherence in speech agents
Lyria 3 by Google Deepmind Turn any photo or thought into a custom song inside Gemini
Gemini 3.1 Pro A smarter model for your most complex tasks
Sonnet 4.6 The most capable Sonnet model yet
Qwen3.5 The 397B native multimodal agent with 17B active params
MiniMax-M2.5 The first open model to beat Sonnet made for productivity