Guide

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Image model for prompt-driven generation, editing, and visual design workflows

Qwen vision-language model for visual reasoning, documents, and agent tasks

Speech transcription model for accurate audio-to-text and captioning workflows

Speech transcription model for accurate audio-to-text and captioning workflows

Video model for prompt-guided generation, editing, and motion workflows

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Qwen vision-language model for visual reasoning, documents, and agent tasks

Specialized search model for knowledge-intensive questions, multi-step retrieval, and evidence synthesis

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Grok model for agentic tool use, reasoning, coding, and live assistance

Flagship DeepSeek model for coding, reasoning, and agentic work

Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows

Nemotron model for efficient reasoning, coding, and specialized AI agents

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

Image model for prompt-driven generation, editing, and visual design workflows

Video model for prompt-guided generation, editing, and motion workflows

Efficient model for low-latency assistance, extraction, and routine automation

Open Llama multimodal model for image understanding and text reasoning

Open Llama multimodal model for image understanding and text reasoning

Image model for prompt-driven generation, editing, and visual design workflows

Multi-agent model for routing expert agents across complex analytical tasks

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

Multimodal reasoning model for visual analysis, planning, and tool use

Video model for prompt-guided generation, editing, and motion workflows

Speech generation model for controllable voice, narration, and audio delivery

Speech generation model for controllable voice, narration, and audio delivery

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Free provider route for experiments, demos, and cost-sensitive chat workloads

Agentic coding model from Poolside in the XS size class for local deployment

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Low-latency Gemini model for high-volume multimodal and agent workloads

Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows

Kimi multimodal agent model for visual understanding, coding, and planning

Kimi multimodal agent model for visual understanding, coding, and planning

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

Qwen vision-language model for visual reasoning, documents, and agent tasks

Image model for prompt-driven generation, editing, and visual design workflows

Cost-efficient GPT-5.6 model for fast, high-volume workloads

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

Balanced GPT-5.6 model for capable, cost-efficient everyday work

GPT model for general reasoning, writing, coding, and tool-assisted tasks

GPT model for general reasoning, writing, coding, and tool-assisted tasks

GPT model for general reasoning, writing, coding, and tool-assisted tasks

Grok model for agentic tool use, reasoning, coding, and live assistance

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Speech generation model for controllable voice, narration, and audio delivery

Everyday Claude agent model for coding, planning, browsing, and general work