gemini-2-5-pro · google · vision
Gemini 2.5 Pro is Google DeepMind's flagship model with a 1M-token context window and best-in-class multimodal capabilities. It supports implicit caching (cache_read 25% input), explicit caching, vision/audio/video understanding, Function Call, code execution, and the Google Search tool.
1M context; implicit caching (cache_read 25% input); explicit caching; vision understanding (images/video/PDF); audio input; Function Call; code execution; Google Search tool; JSON mode.
Multimodal Q&A; video content understanding; long-document analysis; code generation; Agent workflows; Google Workspace integration; image understanding.
No image generation (use Gemini Image); implicit caching is not a guaranteed hit; high concurrency requires a Google Cloud quota; the enterprise edition requires contacting sales.
Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.
export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="gemini-2-5-pro"
claude