Model Catalog

OpenAI flagship multimodal model with vision, audio, and text capabilities. Fast and cost-effective.

OpenAI lightweight and efficient model. Great value for high-volume tasks with excellent performance.

OpenAI's latest GPT-4.1 model with improved coding, instruction following, and long-context performance.

Compact version of GPT-4.1. Excellent balance of capability and cost for most tasks.

Smallest GPT-4.1 variant. Ultra-fast and cost-effective for simple tasks.

OpenAI classic model. Fast and cost-effective for simple tasks like summarization and classification.

Latest GPT-3.5 Turbo snapshot from Jan 2025. Improved instruction following and JSON mode.

GPT-3.5 Turbo snapshot from Nov 2023. Supports parallel function calling and JSON mode.

Extended context version of GPT-3.5 Turbo with 16K token window for longer conversations.

Stable GPT-3.5 Turbo 16K snapshot from June 2023. Reliable for production use.

Anthropic's most powerful reasoning model. Excels at complex analysis, coding, and research tasks.

Claude Opus 4 with extended thinking. Shows step-by-step reasoning for complex problem solving.

Anthropic's balanced model with extended thinking. Great combination of speed, cost, and intelligence.

Google's fast reasoning model. Combines speed with thoughtful analysis for efficient problem solving.

Google's fast multimodal model with excellent speed and efficiency for general tasks.

Lightweight and fast Gemini model optimized for quick responses and cost efficiency.

Preview version of Gemini 2.5 Flash Lite with experimental features and improvements.

Google's most capable Gemini model with advanced reasoning and comprehensive capabilities.

Preview version of Gemini 2.5 Flash with the latest experimental features.

Fast Gemini model without extended reasoning for quick, direct responses.

Gemini model optimized for image understanding and visual analysis tasks.

Advanced AI image editing and generation model with powerful context-aware capabilities.

High-quality AI image generation with exceptional detail and artistic control.

豆包绘画 5.0 - ByteDance's latest Chinese image generation model with superior quality.

豆包绘画 4.5 - ByteDance's Chinese image generation model with excellent performance.