01
通过 APIMart 用一套兼容 OpenAI 的接口接入全球主流大模型,覆盖文本、图像、视频与多模态能力;统一密钥、统一计费、统一监控,让团队以更低成本快速把生产级 AI 能力接入自己的产品。
把模型能力、成本、密钥、监控与故障切换收敛到统一网关,让团队用一套 OpenAI 兼容接口管理全部 AI 调用。
01
02
OpenAI 兼容
现有 SDK 一行迁移
统一计费
所有模型族共享积分余额
供应商路由
按健康状态跨供应商调度
专属支持
文档、充值与客服在同一流程
OpenAI · Anthropic · Google · ByteDance — 一个账户,一张账单
03
不只是接入。每次请求都会强化成本、路由与可见性。
llms.txt
复制一段提示词到 CodeX、Claude、Cursor 等任意 Agent,让它立刻读懂 APIMart 全部模型和接口,并向其提问。
请阅读以下 APIMart 的文档索引,并基于此回答我的问题:
https://docs.apimart.ai/llms.txt
关于 APIMart:统一的 AI API 网关,通过 OpenAI 兼容协议提供 190+ 模型 —— 聊天(GPT、Claude、Gemini)、图像(Nano Banana、GPT-Image-2、Imagen)、视频(Veo、Kling、Seedance)、音频,按成功请求计费。
我的问题:如何用 Python 调用 Kling V3 生成一段 5 秒的视频?模型
精选各类目顶级模型,几分钟即可开始接入。
Minimax
图像
Built for image quality and prompt adherence. It handles text-to-image, reference-based generation and image editing. MiniMax says it can generate a 4K (4096 × 4096) image in under 10 seconds and work with up to 16 reference images. In Chinese launch coverage, MiniMax puts its speed at about 1.5 to 2 times that of mainstream tools.
$0.08
Minimax
图像
Built for speed. The same coverage puts it at about 3 to 4 times faster than mainstream tools, which suits batch jobs or anything that needs fast turnaround.
$0.152
apimart
图像
Seedream 5.5 brings your imagination to life through expressive visuals. From dreamy illustrations to cinematic scenes and product concepts, explore color, texture, and light to shape images that tell your story.
$0.0228
OpenAI
图像
GPT Image 2.6 Sunburst brings a fresh burst of creativity to your ideas. From vibrant illustrations to atmospheric scenes and striking product concepts, explore rich colors, expressive lighting, and thoughtful compositions that make your vision shine.
OpenAI
图像
GPT Image 2.6 Flare brings your imagination into focus, turning creative ideas into expressive visuals. From cinematic scenes and bold illustrations to polished product concepts, explore color, light, and composition to give every idea its own distinctive look.
apimart
图像
Muse Image turns inspiration into compelling visuals. From a spark of an idea to a fully imagined scene, it helps bring your creative vision to life with images that express your style and tell your story. Explore new possibilities and give every idea a visual voice.
$0.0048
apimart
图像
HY Image 3.5 Preview is an image generation and editing model developed by Tencent Hunyuan. It supports text-to-image creation, reference-based generation, and multi-turn editing, allowing users to refine images through conversational instructions. With support for up to 4K output and flexible image dimensions, it offers a versatile tool for creating and refining visual content.
$0.0192
Layers
图像
FLUX 3 Image Klein is a compact, open-weight image generation and editing model developed by Black Forest Labs. It combines text-to-image creation, image editing, and composition using up to 10 reference images in a single model. With support for up to 4K resolution and bounding-box layout control, it gives creators flexible tools to bring their ideas to life.
$0.0072
Azure
图像
MAI-Image-2.6 Flash is the Flash version of Microsoft MAI-Image-2.6 for text-to-image and image editing with up to 5 references, 1K/2K PNG output and optional Bing grounding, billed by actual token usage.
$0.016
apimart
图像
MAI-Image-2.6 is Microsoft's image model for text-to-image, single-image editing and composition with up to 5 reference images. It is available in high-quality and Flash versions, with 1K and 2K output and sharp text rendering.
$0.032
apimart
视频
apimart-zoe creates 4–30 second videos, or lets the model choose the length, at 480p, 720p, 1080p, 2K or 4K in seven aspect ratios from 21:9 to 9:16. It can work from a text prompt, from first and last frames, or from up to 30 reference images, 10 reference videos and 10 reference audio clips. It can also edit an existing video, changing its style or elements while keeping the original length and framing. Audio can be generated together with the video. A two-step workflow lets you preview a shot as a low-cost 480p draft and then render the approved draft as a 1080p final within 24 hours. Billing is per second of output, with a separate rate for requests that include reference videos.
$0.1836/s
Kling
视频
Kling 4.0 Flash brings your creative vision to life in motion. From cinematic moments to imaginative visual stories, turn your ideas into videos that capture attention, set the mood, and give every scene a story to tell.
$0.0857/s
Gemini
视频
Gemini Omni 1.2 Flash puts your ideas in motion. From everyday questions to creative exploration, bring fresh perspectives to your work, find inspiration, and keep your next project moving forward.
$0.06/s
apimart
视频
Muse Video brings ideas to life through the power of visual storytelling. From everyday inspiration to bold creative concepts, it helps turn your vision into videos that connect, engage, and leave a lasting impression. With creativity at its heart, Muse Video makes every story worth sharing.
$0.0024/s
apimart
视频
PixVerse V6 Max is an advanced AI video generation model that transforms text and images into cinematic videos up to 15 seconds long at 1080p. With realistic visuals, expressive characters, and optional synchronized audio, it offers precise creative control for multi-shot storytelling, advertising, and music videos.
$0.032/s
Kling
视频
Kling 4.0 is an advanced AI video generation model that brings creative ideas to life with realistic motion, dynamic camera work, and precise visual control. With support for continuous videos up to 30 seconds and multiple reference inputs, it helps creators craft cinematic stories with greater flexibility.
$0.14/s
Vidu
视频
Vidu Q4 Preview is ShengShu's image-to-video and reference-to-video model. Animate one first frame or combine up to 15 reference images and 3 audio clips into 3–16 second videos at up to 4K, with audio generated by default.
$0.0912/s
apimart
视频
Wan 3.0 Prime is the Prime version of Alibaba Cloud's all-in-one Wan 3.0 video model, with general, first-and-last-frame and file or webpage modes and 2–30 second output.
$0.2057/s
Gemini
视频
Gemini Omni 1.1 Flash is a multimodal video model officially released by Google that supports rapid generation, natural language editing, and cinematic-quality visual control. This page connects to the official service through APIMart’s unified video API and uses separate pricing and task logs.
$0.088/s
Minimax
视频
MiniMax H3 Max generates video from text and images at 480P, 768P or 1080P with 5–15 second clips, first/last frames, multimodal references and synced audio.
$0.0571/s
Gemini
对话
Gemini-4-Argon is an AI assistant that brings together analytical thinking and creative expression. From untangling complex problems to refining writing and code, it offers clear reasoning, natural conversation, and practical suggestions to help turn rough ideas into actionable next steps.
$1.6/M / $8/M
Claude
对话
Claude Haiku 5.5 API on APIMart delivers fast, cost-efficient AI, offering responsive conversations, capable coding assistance, and reliable performance for high-volume workflows.
$0.08/M / $0.4/M
Claude
对话
Claude Opus 5 is Anthropic’s next-generation flagship large language model, featuring enhanced capabilities in code development, complex reasoning, knowledge analysis, and agent execution, making it ideal for large-scale project development and professional work scenarios.
$4/M / $20/M
Moonshot
对话
Kimi-K3 is a next-generation large language model launched by Moonshot AI. It features ultra-long context, multimodal understanding, and strong coding capabilities, making it suitable for complex reasoning, software development, knowledge analysis, and agent automation tasks.
$2.4/M / $12/M
Gemini
对话
A lightweight multimodal model launched by Google that emphasizes low cost, low latency, and high throughput. It is suitable for document parsing, data extraction, structured output, and large-scale agent workflows, delivering faster response times while maintaining core reasoning capabilities.
$0.24/M / $2/M
Gemini
对话
Gemini 3.6 Flash is a faster, more token-efficient, and more code-capable version of the Gemini Flash model, suitable for everyday development, AI agents, and high-concurrency applications.
$1.2/M / $6/M
Moonshot
对话
Kimi has launched a high-speed code model that focuses on code generation, autocompletion, debugging, and development tasks, balancing programming capabilities with responsiveness.
$1.49/M / $6.17/M
Minimax
对话
MiniMax has launched a new generation of large language models that enhance reasoning, coding, and agent capabilities, making them suitable for handling complex tasks and developing intelligent applications.
$0.24/M / $0.96/M
XAI
对话
xAI has launched a code development model focused on software development, code generation, debugging, and engineering tasks, suitable for AI programming assistants and agent scenarios.
$0.8/M / $1.6/M
Moonshot
对话
A code-specific model launched by Moonshot AI that excels at code generation, understanding, debugging, and complex development tasks, and is suitable for use as an AI programming assistant.
$0.74/M / $3.08/M
几分钟内即可开始使用数百种 AI 模型
curl --request POST \
--url https://api.apimart.ai/v1/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-4o",
"messages": [
{
"role": "system",
"content": "You are a professional AI assistant."
},
{
"role": "user",
"content": "Tell me about the history of artificial intelligence."
}
]
}'为什么选择 APIMart
统一平台、透明计价、真人支持,让你专注于产品本身。
聚合官方与认证渠道,链路清晰,告别层层转手。
按 token / 按次计费一目了然,方便做成本预测。
密钥、配额、用量在多模型间统一查看与管理。
兼容常见调用格式,示例代码改配置即可跑通。
多模型组合与用量阶梯,让规模使用更划算。
集成与账单问题有工程师跟进,不靠纯机器人。
常见问题
APIMart是一个统一的AI API平台,通过单一API提供190+ AI模型的访问。可调用聊天API(GPT-6.1、Claude Opus 5.5、Gemini 3.8)、视频API(Veo 3.1、Seedance 2.5)和图像API(GPT Image 2、Nano Banana Pro),兼容OpenAI集成,价格低于官方 20%。
APIMart上的所有模型均低于官方提供商价格 20%,铂金和钻石会员最高可省 28%。按量付费,无最低月费或隐藏费用,只为成功的请求付费。
简单的集成:1)注册并创建API密钥,2)将您的base_url更新为APIMart的端点,3)开始使用OpenAI兼容格式。对于OpenAI用户,通过全面的文档和示例,只需更改一行代码。
使用APIMart,您只需管理一个账户和一张发票即可访问190+款AI模型。无需再为Claude、OpenAI和Google分别维护API Key。此外,所有模型均低于官方价 20%。
您的密钥在数据库中经过加密存储。您可以在控制台随时生成新密钥或撤销旧密钥,以确保账户安全。
APIMart支持多种主流支付渠道:Antom(Visa、Mastercard、支付宝)、Crypto加密货币、PayPal,以及Creem。您可在控制台选择套餐后按地区可用渠道完成支付,所有充值记录均可在账单页面查询导出。如需正规电子发票或对公汇款,请联系我们的支持团队协助办理。
APIMart完全兼容OpenAI接口规范,因此官方OpenAI客户端(Python、Node.js、Go、Java、PHP、C#、Ruby等)只需替换base_url即可直接使用,无需引入额外依赖。同样兼容LangChain、LlamaIndex、Vercel AI等主流框架。
默认账户即提供较高的RPM/TPM配额,企业账户可申请独立配额与专属通道。APIMart 聚合多家上游供应商,通过统一 API 提供服务,并以多区域多供应商自动路由与故障转移降低单点风险。失败的请求不计费,每次请求与用量都可在控制台的请求日志中查看。
不会。APIMart仅将您的请求转发至所选模型供应商完成本次推理,不会留存或将您的输入输出用于任何模型训练。同时我们透传各供应商的零数据保留(ZDR)协议,企业账户可签署DPA,满足GDPR、SOC 2等合规需求。