模型

DeepSeek: DeepSeek V4.1 Flash Heretic推荐无审查思考识图512K 上下文

DeepSeek V4.1 Flash 的 heretic 去审查版本，推理和代码能力强。

智谱: GLM-5.3 Flash Abliterated推荐无审查思考识图1M 上下文

去除拒答方向的 GLM-5.3 Flash，比无审查微调版更便宜，回答更直接。

DeepSeek: DeepSeek V4.1 Flash 无审查版推荐无审查思考识图1M 上下文

DeepSeek V4.1 Flash 无审查微调版，1M 上下文，综合能力均衡。

小米: MiMo V2.6 Flash 无审查版推荐无审查思考识图1M 上下文

MiMo V2.6 Flash 无审查版，响应快，适合对话和批量生成。

智谱: GLM-5.3 Flash 无审查版推荐无审查思考识图1M 上下文

GLM-5.3 Flash 的无审查微调版本，长上下文、中文写作和角色扮演表现好，适合小说创作和酒馆。

Meta: Muse Ember思考识图1.05M 上下文

Meta's Muse Ember is the smallest and most efficient Muse model, built for the work agents repeat all day: tool calls, coding-agent subtasks, routing, and extraction. It accepts text, images, audio, video, and PDF docu…

Google: Gemini 4 Carbon思考识图1.05M 上下文

Google's Gemini 4 Carbon is a reasoning model for complex coding, scientific and mathematical problem solving, and multi-step tasks that use tools. It accepts text, images, audio, video, and PDFs and produces text, wit…

百度: ERNIE Light DT 1.0 (Intl)思考1.02M 上下文

ERNIE Light DT 1.0 (Intl) is text model with Sparse Attention for working with long conversations and documents. It supports tool calling, structured output, a 1,024,000-token context window, and up to 131,072 output t…

社区: Nex N2.6思考识图262K 上下文

Nex N2.6 is Nex AGI's agentic model for coding and long-running tasks that use tools. It accepts text and images, produces text, and supports tool calling and structured output within a 262,144-token context window. Re…

Anthropic: Claude Fable 5.2思考识图1M 上下文

Anthropic's Claude Fable 5.2 supports demanding reasoning, coding, and long-running agentic work, with text, image, and PDF inputs, tool calling, and structured outputs. It has a 1M-token context window and up to 128K …

An OrcaCyber model built on DeepSeek V4.1 Flash for authorized security research, coding, and tool use. Accepts text and images, with reasoning off by default. Supports a 1M-token context window, up to 393K output toke…

An OrcaCyber model built on DeepSeek V4.1 Flash for authorized security research, coding, and tool use. Accepts text and images, with reasoning on by default. Supports a 1M-token context window, up to 393K output token…

An OrcaCyber model built on GLM 5.3 Flash for authorized security research, coding, and tool use. Accepts text and images. Reasoning is always enabled, with selectable effort. Supports a 1M-token context window, up to …

An OrcaCyber model built on MiMo V2.6 Flash for authorized security research, coding, and tool use. Accepts text input, with reasoning enabled by default and an option to turn it off. Supports a 1M-token context window…

Moonshot: Kimi K3.1 Pro 私密计算版思考识图262K 上下文

Kimi K3.1 Pro is Moonshot AI's multimodal model post-trained from Kimi K3 for long-horizon coding, agentic workflows, and knowledge work. It always reasons, and supports image input, tool calling, and structured output…

Qwen: DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic无审查33K 上下文

Uncensored Heretic version of Jackrong's DeepSeek V4 Pro Qwen3.5 9B, a Qwen3.5 9B model distilled from DeepSeek V4 Pro on about 250,000 math and STEM samples. It answers directly without a thinking phase. It accepts an…

Liquid: LFM3 1.7B思考262K 上下文

Liquid AI's compact 1.7B-parameter text model for tool use, structured output, data extraction, and specialized agents. It reasons before answering and supports a 262,144-token context window with up to 8,192 output to…

inclusionAI: Ling 3.0 Tiny262K 上下文

Ling 3.0 Tiny is a compact 7.9B-parameter Mixture-of-Experts model with 1.3B parameters active per token. It is designed for responsive agents, reliable instruction following, natural multi-turn conversations, long-con…

inclusionAI: Ling 3.0 Tiny Thinking思考262K 上下文

Ling 3.0 Tiny Thinking enables visible reasoning on inclusionAI's compact 7.9B-parameter Mixture-of-Experts model for harder agent tasks, coding, planning, function calling, and long-context workflows.

Google: Artemis 31B v1.2角色扮演66K 上下文

Gemma 4 31B finetune for creative writing, character roleplay, and conversation. It accepts and returns text, with a 65,536-token context window shared by input and output and up to 8,192 output tokens.

社区: Ripple 65B Preview思考16K 上下文

Ripple 65B Preview is Ricursive Intelligence's Apache 2.0-licensed, 65-billion-parameter reasoning model for coding and agentic tasks. It accepts and returns text, supports automatic tool calling and JSON output, and h…

An OrcaRouter model for authorized security research, coding, and tool use. Accepts text and images, with reasoning enabled by default and an option to turn it off. Supports a 1M-token context window, up to 943K output…

腾讯: Tencent Hy4思考识图1.05M 上下文

Tencent Hy4 accepts text and images and returns text, with a 1,048,576-token context window and up to 65,536 output tokens. It supports coding, long-document analysis, automatic tool calling and structured output. Reas…

Qwen: Assistant Pepe 32B角色扮演41K 上下文

Assistant Pepe 32B is Qwen3-32B finetune for creative writing, brainstorming, roleplay and irreverent conversation. Trained on UBW Tapestries, it has a built-in conversational persona and replies without a separate thi…

智谱: GLM 5.3 FlashX Legal思考识图1.05M 上下文

GLM 5.3 FlashX Legal is Z.AI's model trained for legal document analysis, contract review, legal reasoning and initial drafts. It accepts text and images and returns text, with always-on reasoning, tool calling, JSON o…

An OrcaCyber model for authorized security research, coding, and tool use. Reasoning is always enabled, with selectable effort. Supports a 262K-token context window, up to 131K output tokens, tool calling, and structur…

An OrcaCyber model for authorized security research, coding, and tool use. Accepts text and images, with reasoning enabled by default and an option to turn it off. Supports a 262K-token context window, up to 131K outpu…

DeepSeek: DeepSeek V4.1 Flash Heretic Thinking无审查思考识图512K 上下文

Heretic checkpoint of DeepSeek V4.1 Flash 1017, served by Sable at original mixed precision (FP8 dense/Engram and MXFP4 experts). Supports text and image input, tools, structured output, and optional reasoning. Separat…

OrcaRouter's frontier cybersecurity model, post-trained for authorized security research: vulnerability research and reproduction, exploit development, penetration testing, and security auditing. Supports a 1M-token co…

社区: Particle-1思考识图1.05M 上下文

Particle-1 is Particle AI’s coding and data-engineering model, post-trained on DeepSeek V4.1 Flash. It accepts text and images, supports tool calling, and offers a shared 1,048,576-token context window with up to 131,0…