Model List & Capability Comparison
Models & Pricing
Model List & Capability Comparison View all AI models supported by the platform and their capability comparisons
The platform aggregates hundreds of models from major providers including OpenAI, Anthropic, Google, and DeepSeek. The following is an overview of the primary model families.
Model Family Representative Models Context Window Key Features OpenAI GPT GPT-5.5, GPT-5.4, GPT-5.4-mini, GPT-5.4-nano 1M Flagship performance; supports vision and function calling Anthropic Claude Claude Opus 4.7, Claude Sonnet 4.6, Claude Haiku 4.5 1M Exceptional at long-document comprehension, writing, and coding Google Gemini Gemini 3.5 Flash, Gemini 3.1 Pro 1M Ultra-long context; cutting-edge performance for agents and code DeepSeek DeepSeek-V4 Pro, DeepSeek-V4 Flash 64K Excellent Chinese comprehension and code generation; very cost-effective Alibaba Qwen Qwen3-235B, Qwen3-72B 128K Optimized for Chinese use cases; enterprise-grade applications Meta Llama Llama 4 Scout, Llama 3.3 128K Open-source models with high value-for-money
Model Context Window Vision Function Calling Reasoning Best For GPT-5.5 1M ✅ ✅ ⭐⭐⭐⭐⭐ Flagship reasoning, code, professional tasks GPT-5.4 1M ✅ ✅ ⭐⭐⭐⭐⭐ General chat, code, professional tasks GPT-5.4-mini 400K ✅ ✅ ⭐⭐⭐⭐ High-frequency, low-cost tasks GPT-5.4-nano 200K ✅ ✅ ⭐⭐⭐ Ultra-low cost, high throughput Claude Opus 4.7 1M ✅ ✅ ⭐⭐⭐⭐⭐ Best-in-class reasoning, code, long documents Claude Sonnet 4.6 1M ✅ ✅ ⭐⭐⭐⭐⭐ Balanced speed and intelligence Claude Haiku 4.5 200K ✅ ✅ ⭐⭐⭐⭐ Fastest response; lightweight tasks Gemini 3.5 Flash 1M ✅ ✅ ⭐⭐⭐⭐⭐ Agents, code, frontier performance Gemini 3.1 Pro 1M ✅ ✅ ⭐⭐⭐⭐⭐ Complex tasks, multimodal DeepSeek-V4 Pro 64K ❌ ✅ ⭐⭐⭐⭐ Chinese comprehension, code generation DeepSeek-V4 Flash 64K ❌ ✅ ⭐⭐⭐⭐ Cost-effective reasoning Qwen3-235B 128K ✅ ✅ ⭐⭐⭐⭐ Chinese scenarios, enterprise applications
Model Key Features DALL·E 3 From OpenAI; rich style variety; supports non-English prompts Flux High-quality photorealistic style with excellent detail rendering Stable Diffusion Open-source; diverse styles; deployable locally Midjourney Outstanding for artistic creation and design styles
Model Type Key Features Whisper Speech-to-Text (STT) Supports multilingual audio-to-text transcription TTS-1 Text-to-Speech (TTS) Fast; suitable for real-time scenarios TTS-1-HD Text-to-Speech (TTS) Higher audio quality; suitable for content production
Model Type Use Case text-embedding-3-small Embedding Lightweight vectorization; suitable for large-scale text batches text-embedding-3-large Embedding High-precision vectorization; suitable for knowledge base retrieval Rerank series Rerank Re-ranks retrieval results to improve RAG accuracy
For the full model list and real-time pricing, see the "Pricing" page in the console. For billing rules, see Billing Rules .
Use Case Recommended Models Everyday Q&A, chatbots GPT-5.4-mini, Gemini 3.5 Flash Code generation & debugging Claude Sonnet 4.6, DeepSeek-V4 Pro Complex reasoning, math GPT-5.5, Claude Opus 4.7 Long-document processing Gemini 3.1 Pro (1M context), Claude Opus 4.7 Chinese language scenarios DeepSeek-V4 Pro, Qwen3-235B Image understanding GPT-5.4, Gemini 3.5 Flash, Claude Sonnet 4.6 Image generation DALL·E 3, Flux, Midjourney Speech recognition Whisper Text-to-speech TTS-1, TTS-1-HD
