Text Models

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

Qwen role-playing model optimized for persona fidelity, instruction following, proactive topic progression, and empathetic dialogue.

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

doubao-seed-2-1-pro-260628 is a model from ByteDance for text generation, reasoning, and assistant workflows.

doubao-seed-2-1-turbo-260628 is a model from ByteDance for text generation, reasoning, and assistant workflows.

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

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding (site alias/snapshot: qwen3.7-plus-2026-05-26).

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks (site alias/snapshot: qwen3.7-max-2026-05-20).

doubao-seed-2-0-lite-260428 is a fully multimodal understanding model designed for large-scale enterprise deployment. It accepts text, image, video, and audio inputs and produces text, supporting joint audio-visual reasoning, long-video temporal retrieval, detailed audio analysis, coding, agent workflows, and GUI interaction.

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

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

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters.

Strong GLM coding model for agentic engineering, terminals, and repository generation

Earlier Qwen multimodal workhorse for million-token agent and document tasks

Earlier Qwen multimodal workhorse for million-token agent and document tasks (site alias/snapshot: qwen3.6-plus-2026-04-02).