DeepSeek V4 Flash 0731 is an efficient MoE model optimized for fast reasoning, coding, and enhanced agentic workflows.

GLM 5.3 Flash is a fast, cost-efficient multimodal model built for long-context reasoning and scalable workflows.

Kimi K3 is a frontier open-weight multimodal model built for long-horizon reasoning, coding, and advanced agentic workflows.

Qwen3.8 27B is a compact open-weight multimodal model optimized for efficient reasoning, coding, and agentic workflows on local hardware.

GLM-5.3 is a flagship open-weight model optimized for advanced coding, agentic workflows, and long-context reasoning.

GLM-5.2 is a flagship model built for long-horizon agentic tasks with stable 1M-token context and advanced coding capabilities.

Claude Opus 5.5 is Anthropic’s most capable Opus model, built for high-end coding and long-running agent workflows.

Claude Opus 5 is Anthropic’s most advanced Opus model, built for long-running agents, complex coding, and high-level professional workflows.

Claude Sonnet 5 is a high-performance model optimized for coding, agent workflows, and everyday professional tasks with strong efficiency and scalability.

Gemma 4 31B IT is a multimodal instruction-tuned model from Google DeepMind designed for strong reasoning, coding, and vision-language tasks.

Claude Opus 4.8 is a top-tier model built for sustained autonomous work, excelling in coding, agents, and complex enterprise tasks.

Claude Opus 4.7 is Anthropic’s most capable general model, optimized for coding, enterprise workflows, multimodal reasoning, and long-running agentic tasks.

Qwen3.5-9B is a dense multimodal model delivering strong reasoning, coding, and visual understanding with efficient performance and long context.

DeepSeek V4.1 Flash is an efficient multimodal MoE model optimized for fast agentic reasoning and coding workflows.

Mistral OCR 4.0 is a document model focused on structured text extraction with layout-aware understanding.

Mistral OCR 3 is an efficient document AI model for structured text extraction and LLM-ready document conversion.

FLUX 2 klein is a compact, high-speed text-to-image model optimized for efficient image generation and editing in low-latency environments.

GPT-5.6 Sol is the flagship model of the GPT-5.6 family, built for advanced reasoning, deep research, and complex multi-step execution.

GPT-5.6 Terra is a balanced mid-tier model optimized for professional work, combining strong reasoning, coding ability, and efficiency.

GPT-5.6 Luna is a fast, cost-efficient model optimized for high-volume tasks, real-time interactions, and lightweight reasoning.

Kimi K2.7 Code is an open-source agentic coding model optimized for long-horizon software engineering and efficient multi-step execution.

MiniMax M3 is a multimodal frontier model built for coding and agentic workflows, featuring ultra-long context and advanced tool-driven reasoning.

Qwen3.6 35B A3B is a lightweight multimodal MoE model focused on efficient agentic coding, long-context reasoning, and visual understanding.

Gemma 4 26B A4B is a multimodal Mixture-of-Experts model optimized for fast, efficient inference with strong reasoning, coding, and agentic capabilities.

DeepSeek-V4 is a Mixture-of-Experts model series featuring advanced attention mechanisms and large-scale training for efficient long-context reasoning and strong performance.

Mistral Medium 3.5 is a frontier multimodal 128B model combining reasoning, coding, and instruction-following with strong agentic performance and efficient deployment.

GPT-5.4 is a frontier model designed for fast, reliable performance across professional workflows, coding, data analysis, and agentic tasks.

Kimi K2.6 is an advanced multimodal agentic model with strong long-horizon coding, instruction following, and autonomous execution capabilities.

GLM-5.1 is a next-generation flagship model for agentic engineering, excelling in long-horizon reasoning and advanced coding tasks.

GPT-6 Sol is a balanced mid-tier model offering strong coding, data analysis, and multi-step reasoning capabilities.