Guide

Claude workhorse for coding agents, careful analysis, and production cost control

Claude workhorse for coding agents, careful analysis, and production cost control

Claude workhorse for coding agents, careful analysis, and production cost control

Claude workhorse for coding agents, careful analysis, and production cost control

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

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

Claude workhorse for coding agents, careful analysis, and production cost control

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

Claude workhorse for coding agents, careful analysis, and production cost control

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

Large open Qwen multimodal MoE for visual agents and long technical tasks

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

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

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

Large open Qwen multimodal MoE for visual agents and long technical tasks

DeepSeek-V3.2 from AWS Bedrock - text input, 163,840 token context

Large open Qwen multimodal MoE for visual agents and long technical tasks

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

Large open Qwen multimodal MoE for visual agents and long technical tasks

ByteDance Seed coding model for multimodal software engineering and long-running agents

Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks

Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows

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

High-speed MiniMax model for low-latency coding and agent workflows

High-speed MiniMax model for low-latency coding and agent workflows

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

MiniMax-M2.5 from Fireworks AI - text input, 196,608 token context

Prior MiniMax coding model for agent workflows, office edits, and automation

GLM 5 TEE from Chutes - text input, 202,752 token context

MiniMax M2.5 TEE from Chutes - text input, 196,608 token context

GLM-5 from Synthetic - text input, 196,608 token context

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

Prior MiniMax coding model for agent workflows, office edits, and automation

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

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

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

Legacy model retained for compatibility with older integrations

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

Prior MiniMax coding model for agent workflows, office edits, and automation

Prior MiniMax coding model for agent workflows, office edits, and automation

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

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

High-speed MiniMax model for low-latency coding and agent workflows

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

GLM 5 from Fireworks AI - text input, 202,752 token context

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

Qwen3.5-97B-A17B from Synthetic - text, image input, 262,144 token context

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