Available Models

OpenAI 2026 latest flagship, 1M context, all-around champion

GPT-5.4 Pro version, ultimate reasoning and code generation

GPT-5.4 lightweight version, fast and cost-effective

GPT-5.4 ultra lightweight, extremely low latency and cost

OpenAI GPT-5 flagship, breakthrough capabilities

GPT-5 enhanced version, stronger reasoning capabilities

OpenAI 2025 flagship, strongest overall capabilities

OpenAI lightweight model, cost-effective

OpenAI open source model, 120B parameters

Anthropic 2026 latest flagship, coding and reasoning fully upgraded

Anthropic 2026 most powerful flagship, autonomous agent task completion

Claude lightweight version, fast response, most cost-effective

Claude main model, balancing capability and cost

Claude flagship model, complex task handling

Google 2026 most powerful flagship, code and reasoning breakthrough

Gemini 3.1 lightweight, optimized for speed and cost

Gemini 3.1 image generation, text-to-image capability

Google Gemini 3 flagship model

Gemini 3 lightweight, fast and efficient

Google 2025 flagship, strong code and reasoning

Gemini 2.5 lightweight, optimized for speed and cost

xAI latest reasoning model, fast deep thinking

xAI fast model, ultra-fast response

xAI code-focused model, strong programming capabilities

Zhipu flagship model, strong Chinese capabilities

Zhipu lightweight model, cost-effective

Moonshot lightweight model, 8K context

Moonshot medium model, 32K context

Moonshot flagship model, 128K ultra-long context

DeepSeek latest generation general chat model, extremely cost-effective

Deep reasoning model, excels at complex logic and math reasoning

Qwen flagship model, strongest overall capabilities

Enhanced model, balancing capability and cost

Fast response model, suitable for high-concurrency scenarios

Qwen reasoning model, deep thinking and logical reasoning

Long text specialized model, supports ultra-long context

Zhipu flagship model, fastest GLM-5 variant with 200K context

Zhipu GLM-5 flagship, advanced reasoning and generation

Zhipu enhanced model with 200K context window

Zhipu balanced model, strong Chinese language capabilities

Zhipu lightweight model, highly cost-effective

MiniMax latest flagship with 205K context, advanced reasoning

MiniMax advanced model with 205K context window

MiniMax enhanced model, strong multilingual support

MiniMax base model, reliable and efficient

Xiaomi flagship AI model with 1M context window

Xiaomi multimodal AI model with 262K context

Qwen3.5 largest model, 397B parameters with MoE architecture

Qwen3 instruction-tuned model with 1M context window

Qwen3 code-specialized model, strongest coding capabilities

Moonshot Kimi latest flagship with 262K context

Kimi deep reasoning model with chain-of-thought

Kimi balanced model, strong general capabilities

DeepSeek latest reasoning model, advanced problem solving

DeepSeek V3.1 enhanced model, improved capabilities

DeepSeek V3.2 latest model, most cost-effective

Google experimental model, optimized for image generation

Google Nano Banana Pro, advanced multimodal capabilities

Google Nano Banana base model, efficient and versatile