Guide

Fast DeepSeek model for efficient chat, coding help, and agent loops

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

Efficient GLM model for fast reasoning, coding, and agent workflows

Fast DeepSeek model for efficient chat, coding help, and agent loops

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

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

Flagship DeepSeek model for coding, reasoning, and agentic work

Qwen instruction model for multilingual chat, reasoning, and tool use

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

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

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

Multimodal model for analyzing text, images, documents, and rich media

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

Open flagship GLM for long-horizon coding agents and million-token context work

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

MiniMax multimodal model for long-context coding, perception, and agent planning

Newer StepFun flash model for faster agents, coding, and multimodal prompts

Open MoE flagship with million-token context for coding and long agent runs

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

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

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

MiMo model for long-context reasoning, perception, and agentic tasks

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

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Open Gemma instruction model for efficient chat and self-hosted deployments

MiniMax model for chat, coding, office work, and agentic tasks

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

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

Qwen instruction model for multilingual chat, reasoning, and tool use

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

MiniMax model for chat, coding, office work, and agentic tasks

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

Qwen coding model for software agents, repository edits, and code reasoning

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

StepFun flash lane for quick multimodal reasoning and coding assistance

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

MiniMax model for chat, coding, office work, and agentic tasks

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

MiMo flash model for fast multimodal assistance and agent workflows

GLM vision model for visual reasoning, documents, and multimodal agents

DeepSeek chat model for instruction following, coding, and analysis

Kimi reasoning model for long-horizon research, planning, and tool use

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Late GLM-4 workhorse for coding agents, reasoning, and structured tasks

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

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

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen reasoning model for deliberate problem solving, math, and coding

Kimi model for long-context chat, coding, and agentic reasoning