Search FoxAI
AI Models 282
- Kimi K2.5↗
月之暗面 · Kimi
kimi-k2.5 支持同时处理文本、图像或视频输入,并可通过 enable_thinking 参数开启思考模式
- Nano Banana 2 (Gemini 3.1 Flash Image Preview)↗
Google
Google最新的 nano-banana-2 第二代绘图模型,一致性极强, 快速版本,核心能力一览: 分辨率:最高 4K(4096×4096),与 Pro 持平参考图一致性:最多 14 张参考图(10 物体 + 4 角色),保持风格/角色一致极端比例:新增 1:4、4:1、1:8、8:1,适合长图、海报、Banner文字渲染:进阶文字生成,适合信息图、营销海报排版搜索增强:集成 Google Search + Image Search grounding思考链:内置 thinking process,复杂 prompt 先推理再生成 支持gemini、openai chat、openai dall-e 接口格式
- gemini-3.8-flash-thinking-medium↗
Google
Gemini 3.8 Flash 是我们最智能的 Flash 模型,专为长远软件工程、自主代理和复杂企业工作流程设计——所有这些都具备 Flash 的速度和成本效益。
- GPT-5.3-Codex↗
OpenAI
GPT-5.3-Codex通过性能提升、功能泛化和安全性升级,重新定义了AI在编程及泛生产力领域的角色
- kling-image↗
快手 · 可灵
最懂中文的图像生成大模型”:基于LLM大语言模型、数十亿中文语料训练,综合指标超过SDXL/SD3等开源模型和Midjourney等闭源模型,实现中文场景下的SOTA。 积分减扣与官方一致
- Kimi K3.1 Pro↗
Kimi
Kimi-K3.1-Pro is Moonshot’s flagship domestically developed multimodal large model, supporting an ultra-long context of up to one million tokens. It can process text, images, and lengthy documents, and boasts powerful reasoning, coding, and tool‑calling capabilities, making it ideal for in-depth analysis, complex agent tasks, and the interpretation of charts and blueprints.
- grok-imagine-image-quality↗
xAI
Grok Imagine Image Quality API:xAI grok-imagine-image-quality 1K 每张 $0.04 起,支持 2K 输出和最多 3 张参考图编辑。
- CyberRealisticXL_Desire↗
cyberdelia
**CyberRealistic XL Desire** is a photorealistic image generation model based on **Stable Diffusion XL 1.0 (SDXL)**. It is designed to produce highly realistic, cinematic-quality outputs with minimal prompt engineering. This checkpoint is optimized for portraits, fashion, and editorial-style scenes, but also handles a wide range of creative prompts with remarkable fidelity.
- GPT-5.6 Terra↗
OpenAI
对于复杂的推理和编码,可以选择 GPT-5.6 Sol;对于智能和成本之间的平衡,可以选择 GPT-5.6 Terra;对于对成本敏感、高容量的工作负载,可以使用 GPT-5.6 Luna。 所有最新的 OpenAI 模型均支持文本和图像输入、文本输出、多语言功能以及视觉识别。这些模型可通过 Responses API 使用。
- Gemini 4 Argon↗
Google
The special offer group model is implemented by partially eligible accounts, using specific parameter requests to invoke Gemini 3.8 Flash. It has been confirmed that upstream traffic is indeed routed to Gemini 4. These are different checkpoints within Gemini 4; reportedly, b performs slightly better than a, but b currently has a lower level of reasoning. The exact IQ should be assessed through actual customer testing.
