gpt-4o · OpenAI · vision
GPT-4o is OpenAI's multimodal model, offering 128K context with support for text, image, and audio input. cached_input automatically caches prefixes at half price. As the multimodal upgrade to GPT-4 Turbo, it offers better value and speed than its predecessor.
128K context; cached_input automatic caching (50% of input); Function Calling; Structured Output; visual understanding; JSON mode; audio input; Batch API at half price.
Multimodal conversation; image understanding; code generation; structured data extraction; enterprise customer support; knowledge base Q&A; voice interaction.
Does not generate images (use DALL·E); no native cache_write support; high concurrency requires a quota increase; max_tokens capped at 16K.
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="gpt-4o"
claude