MediaGo Model Marketplace

Choose generation models by capability

Browse the currently available text, image, video, and audio models, including supported inputs, output specs, usage, and credit pricing.

Model providers

Choose a provider to view its supported model versions.

All models

13 available model versions.

Get API key
Text Gemini

Gemini 2.5 Flash

gemini-2.5-flash

Fast cost-effective Gemini text and multimodal model for summary, Q&A and lightweight analysis.

text chat fast vision

Price

Input 165 credits/1M · Output 1375 credits/1M

Capability

Vision input · Tool calling · 1048576 token context

Usage 0 runs / 0 credits
gemini-2.5-flash-image

Nano Banana 图片生成与编辑模型,适合快速出图、图像编辑和创意迭代。

image nano-banana text-to-image reference-image

Price

28 credits / call

Capability

Reference image generation · 1K

Usage 0 runs / 0 credits
gemini-3-pro-image

Nano Banana Pro 图片模型,支持 1K/2K/4K 分辨率和多种宽高比。

image nano-banana-pro text-to-image reference-image

Price

Input 642 credits/1M · Output 38544 credits/1M

Capability

Reference image generation · 1K / 2K / 4K

Usage 0 runs / 0 credits
gemini-3.1-flash-image

Nano Banana 2 图片模型,支持更高分辨率,适合通用视觉创作。

image nano-banana text-to-image reference-image

Price

Input 100 credits/1M · Output 12045 credits/1M

Capability

Reference image generation · 1K / 2K / 4K

Usage 0 runs / 0 credits
gemini-3.1-flash-lite-image

低成本高速的 Gemini 图片模型,适合速度优先的图片生成和轻量编辑。

image nano-banana text-to-image reference-image

Price

Input 136 credits/1M · Output 16381 credits/1M

Capability

Reference image generation · 1K / 2K / 4K

Usage 0 runs / 0 credits
gemini-3.1-pro-preview

Long-context multimodal reasoning model for complex analysis, vision and large-context tasks.

text chat reasoning vision

Price

Input 1100 credits/1M · Output 6600 credits/1M

Capability

Vision input · Tool calling · 1048576 token context

Usage 0 runs / 0 credits
Text Gemini

Gemini 3.5 Flash

gemini-3.5-flash

Fast Gemini text model for complex coding, agent and long-running tasks.

text chat reasoning coding

Price

Input 819 credits/1M · Output 4914 credits/1M

Capability

Vision input · Tool calling · 1048576 token context

Usage 0 runs / 0 credits
Image OpenAI

GPT Image 2

gpt-image-2

适合高质量文生图、参考图生成与图片编辑,支持多种尺寸和画质档位。

image text-to-image reference-image image-edit

Price

Input 2730 credits/1M · Output 16381 credits/1M

Capability

Reference image generation · 1K / 2K / 4K

Usage 15 runs / 300 credits
happyhorse-1.1-i2v

阿里云百炼 HappyHorse 1.1 图生视频模型,以首帧图片生成 3 至 15 秒有声视频。

video happyhorse image-to-video first-frame

Price

About 495-660 credits / 5s

Capability

720p / 1080p · 3-15s

Usage 0 runs / 0 credits
happyhorse-1.1-r2v

阿里云百炼 HappyHorse 1.1 参考生视频模型,支持 1 至 9 张角色或风格参考图。

video happyhorse reference-to-video multimodal

Price

About 495-660 credits / 5s

Capability

720p / 1080p · 3-15s

Usage 0 runs / 0 credits
happyhorse-1.1-t2v

阿里云百炼 HappyHorse 1.1 文生视频模型,支持 720p/1080p、3 至 15 秒有声视频。

video happyhorse text-to-video audio

Price

About 495-660 credits / 5s

Capability

720p / 1080p · 3-15s

Usage 0 runs / 0 credits
Image bailian

Wan 2.7 Image

wan2.7-image

阿里云百炼通义万相 2.7 图片模型,支持文生图、多图参考和图片编辑。

image wan text-to-image reference-image

Price

22 credits / call

Capability

Reference image generation · 1K / 2K

Usage 0 runs / 0 credits
Image bailian

Wan 2.7 Image Pro

wan2.7-image-pro

阿里云百炼通义万相 2.7 Pro 图片模型,面向高质量文生图与多图编辑,文生图最高支持 4K。

image wan text-to-image reference-image

Price

55 credits / call

Capability

Reference image generation · 1K / 2K / 4K(仅文生图)

Usage 0 runs / 0 credits