跳到主要内容

AI 模型 API 目录

19 家厂商的 125 个模型系列,一个 API Key 全部调用。对比输入与实时价格,再在 Playground 或代码中运行。

Layout

23 个模型

清除筛选

4K

top resolution

Google

Nano Banana Pro

Google's Nano Banana Pro (Gemini 3.0 Pro Image) is an industry-leading cutting-edge text-to-image model, which can generate high-definition 4K images with excellent quality and has been fully optimized for mobile phone devices to ensure smooth operation. It is equipped with a ready-to-use REST inference API, has the best performance, zero coldstarts, and extremely affordable pricing.

  • 文生图
  • 图生图
正在加载价格…
2 个版本

4K

top resolution

Google

Nano Banana 2

Lightweight text-to-image API built for high concurrency & instant response, with low-latency, budget-friendly image generation and editing. Perfect for scenarios with fast iteration, real-time preview or mass batch image creation. Low-price channel edition: much cheaper than official stable build, but unstable.

  • 图生图
  • 文生图
正在加载价格…
4 个版本

4K

top resolution

OpenAI

GPT Image 2.5

GPT Image 2.5 Sunburst focuses on intricate detail, reliable typography, and controlled composition.

  • 图生图
  • 文生图
正在加载价格…
4 个版本

4K

top resolution

Black Forest Labs

FLUX 3

Generate images from a text prompt.

  • 文生图
  • 图生图
正在加载价格…
4 个版本

2K

top resolution

ByteDance

Seedream 5.0

Generate an image from a text prompt.

  • 文生图
  • 图生图
正在加载价格…
6 个版本

7

aspect ratios

xAI

Grok Imagine 2.0

Grok Imagine 2.0 low-price channel edition provides async text-to-image generation with seven common aspect ratios and 1–12 images per request, billed by successfully delivered images. It suits marketing creatives, social visuals, concept exploration, and cost-sensitive batch generation. This is the channel tier of the formal 2.0 capability; peak stability may trail the official-stable tier.

  • 文生图
正在加载价格…
1 variant

4K

top resolution

OpenAI

GPT Image 2.0

The GPT-Image-2 Text-to-Image is a state-of-the-art generation foundation designed for high-standard commercial scenarios. It features revolutionary text rendering capabilities, flawlessly integrating complex words and phrases into images without spelling errors. It excels in generating modern UI prototypes and design aesthetics, natively supporting ultra-high-definition outputs. With generation speeds nearly doubled, it perfectly empowers workflows like poster design, e-commerce graphics, and product prototyping. 1k/2k/4k available. Due to interface stability limitations, precise 2k/4k output is not guaranteed. Most results will be 1k. Use official API if concerned.

  • 文生图
  • 图生图
正在加载价格…
2 个版本

2

个任务

xAI

Grok Imagine Image

Grok 4.2's text-to-image mode empowers creators to build magnificent visual worlds entirely from scratch. By simply inputting natural language descriptions, the model accurately parses semantics to generate images with ultra-high definition, rich details, and perfect lighting. From complex text typography and photorealistic shots to imaginative fantasy scenes, a single prompt instantly turns creative concepts into vivid reality.

  • 文生图
  • 图生图
正在加载价格…
2 个版本

3,000

prompt characters

Qwen

Qwen Image 3.0

Generate images from text with Qwen Image 3.0 Pro.

  • 文生图
  • 图生图
正在加载价格…
4 个版本

15 s

longest clip

Alibaba

Wan 2.7

Generate images from text with Wan 2.7.

  • 文生图
  • Image tools
  • 文生视频
  • +3
正在加载价格…
9 个版本

800

prompt characters

Qwen

Qwen Image 2.0

Generate images from text.

  • 文生图
  • 图生图
正在加载价格…
4 个版本

10 s

longest clip

Alibaba

Wan 2.5 Preview

Generate images from text.

  • 图生图
  • 文生图
  • 图生视频
  • +1
正在加载价格…
4 个版本

7

aspect ratios

Alibaba

Z Image Turbo

Generate an image from a text prompt.

  • 文生图
  • 图生图
正在加载价格…
4 个版本

4K

top resolution

ByteDance

Seedream 4.7

Generate single images or image sequences from text.

  • 文生图
  • 图生图
正在加载价格…
2 个版本

7

aspect ratios

Black Forest Labs

FLUX.2 Dev

Generate an image from a text prompt.

  • 图生图
  • 文生图
正在加载价格…
2 个版本

7

aspect ratios

Black Forest Labs

FLUX.2 Klein

Generate an image from a text prompt.

  • 文生图
  • 图生图
正在加载价格…
4 个版本

1

任务

Black Forest Labs

FLUX.1 Kontext Dev

Edit a reference image with FLUX.1 Kontext Dev and an optional LoRA model.

  • 图生图
正在加载价格…
1 variant

7

aspect ratios

Alibaba

Qwen Image Edit 2511

Edit one to three reference images with Qwen Image Edit 2511.

  • 图生图
正在加载价格…
2 个版本

2K

top resolution

ByteDance

Seedream 5.5

Generate or edit images with Seedream 5.5.

  • 文生图
  • 图生图
正在加载价格…
4 个版本

7

aspect ratios

Meta

Muse Image

Generate visual content from a prompt and optional reference images.

  • 文生图
正在加载价格…
1 variant

4K

top resolution

Google

Nano Banana 2.1

Generate or edit images from a prompt with Nano Banana 2.1.

  • 文生图
  • 图生图
正在加载价格…
4 个版本

2K

top resolution

Krea

Krea V2

Generate an image from a text prompt with Krea V2 Medium.

  • 文生图
正在加载价格…
2 个版本

32,000

prompt characters

OpenAI

GPT Image 2.6

Generate an image with GPT Image 2.6 Sunburst.

  • 文生图
  • 图生图
正在加载价格…
4 个版本

Image generation and editing APIs

23 image model families from 9 providers. 21 generate images from text and 20 edit or combine existing images. Each one runs as a job through POST /api/v1/jobs, and resolution and aspect ratio are fields of the request.

Compare every price阅读快速开始

选择模型的常见问题

How do I call these models?

Image, video and music models are asynchronous: POST /api/v1/jobs with a model ID and an input object, then poll GET /api/v1/jobs/{id} until the task succeeds. LLMs are synchronous through POST /api/v1/chat/completions, which works with any OpenAI SDK. The quickstart has a request you can copy.

How am I charged?

From prepaid credits, with no subscription. A task's price is reserved when it is accepted and charged only when it succeeds; a failed task returns the reservation. LLMs are charged per token from the usage the model reports. Every rate is on the pricing page.

What is a model variant?

One model page can hold several model IDs: tiers such as Pro and Standard, tasks such as text to video and image to video, or a lower-priced channel. Each variant has its own model ID, input schema and price; pick one on the model page.

Which image models can edit an existing image?

Nano Banana Pro, Nano Banana 2, GPT Image 2.5, GPT Image 2.0, Grok Imagine Image, Qwen Image 3.0, Wan 2.7, Qwen Image 2.0, Wan 2.5 Preview, FLUX 3, and 10 more. Send the source images as HTTPS URLs or upload them with POST /api/v1/media first.

Which image models output 4K?

Nano Banana Pro, Nano Banana 2, GPT Image 2.5, GPT Image 2.0, FLUX 3, Seedream 4.7 和 Nano Banana 2.1. Set the resolution field of the request to 4K.

Why does a model say Price not set yet?

No price is configured for it yet, so it cannot run: the API answers MODEL_PRICE_UNAVAILABLE. The page and its schema stay available for reference.