Guide

DeepSeek V4.1 Flash model for reasoning and agentic coding

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

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

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

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

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

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

Kimi K2.6 from Synthetic - text, image input, 262,144 token context

GLM 5.1 from Synthetic - text input, 196,608 token context

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

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

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

MiniMax-M2.5 from Synthetic - text input, 191,488 token context

Budget GLM lane for fast coding help, routing, and everyday automation

Kimi K2.5 from Synthetic - text, image input, 262,144 token context

Kimi K2.5 (NVFP4) from Synthetic - text, image input, 262,144 token context

MiniMax-M2.1 from Synthetic - text input, 204,800 token context

GLM 4.7 from Synthetic - text input, 200,000 token context

DeepSeek V3.2 from Synthetic - text input, 162,816 token context

Kimi K2 Thinking from Synthetic - text input, 262,144 token context

MiniMax-M2 from Synthetic - text input, 196,608 token context

GLM 4.6 from Synthetic - text input, 200,000 token context

DeepSeek V3.1 Terminus from Synthetic - text input, 128,000 token context

Kimi K2 0905 from Synthetic - text input, 262,144 token context

DeepSeek V3.1 from Synthetic - text input, 128,000 token context

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

DeepSeek R1 (0528) from Synthetic - text input, 128,000 token context

DeepSeek V3 (0324) from Synthetic - text input, 128,000 token context

GLM 4.5 from Synthetic - text input, 128,000 token context

Qwen3 235B A22B Thinking 2507 from Synthetic - text input, 256,000 token context

Qwen 3 Coder 480B from Synthetic - text input, 256,000 token context

Qwen 3 235B Instruct from Synthetic - text input, 256,000 token context

Llama-4-Scout-17B-16E-Instruct from Synthetic - text, image input, 328,000 token context

Llama-4-Maverick-17B-128E-Instruct-FP8 from Synthetic - text, image input, 524,000 token context

DeepSeek R1 from Synthetic - text input, 128,000 token context

DeepSeek V3 from Synthetic - text input, 128,000 token context

Llama-3.3-70B-Instruct from Synthetic - text input, 128,000 token context

Qwen2.5-Coder-32B-Instruct from Synthetic - text input, 32,768 token context

Llama-3.1-70B-Instruct from Synthetic - text input, 128,000 token context

Llama-3.1-8B-Instruct from Synthetic - text input, 128,000 token context

Llama-3.1-405B-Instruct from Synthetic - text input, 128,000 token context