SkyRouter Models

Access 150+ models with a simple API

Power your AI with 150+ Open & Proprietary models for Multimodal Applications

Explore Models:

DeepSeek R1

Text Model
Open-source reasoning model, with long-chain cognitive capabilities and expertise in coding and mathematics
Input Tokens, 1M
$0.55
Output Token, 1M
$2.19

DeepSeek V3

Text Model
MoE architecture to significantly increase output speed and challenge top AI models at lowered cost
Input Tokens, 1M
$0.27
Output Token, 1M
$1.1

GPT 4.1

Text Model
Smartest model for complex tasks, with strong coding capabilities, high model robustness, and multi-task processing advantages
Input Tokens, 1M
$2.00
Output Token, 1M
$8.00

GPT 4.1 mini

Text Model
Smartest model for complex tasks, with strong coding capabilities, high model robustness, and multi-task processing advantages
Input Tokens, 1M
$0.40
Output Token, 1M
$1.60

GPT 4.1 nano

Text Model
Affordable model balancing speed and intelligence
Input Tokens, 1M
$0.10
Output Token, 1M
$0.40

GPT o3

Text Model
Fastest, most cost-effective model for low-latency tasks
Input Tokens, 1M
$2.00
Output Token, 1M
$8.00

GPT o4 mini

Text Model
A lightweight and cost-efficient version, optimized for simpler tasks and faster responses, ideal for everyday use
Input Tokens, 1M
$1.10
Output Token, 1M
$4.40

GPT 4o

Text Model
A multimodal model capable of handling text, images, and audio, excelling in real-time interactions
Input Tokens, 1M
$2.50
Output Token, 1M
$10.00

GPT 4o mini

Text Model
A compact and cost-effective variant of GPT 4o, offering 80% of its capabilities with reduced computational requirements
Input Tokens, 1M
$0.15
Output Token, 1M
$0.60

Gemini 2.5 Pro

Text Model
A recommended model preview version that showcases superior performance across multiple aspects
Input Tokens, 1M
From $1.25
Output Token, 1M
From $10.00

Gemini 2.5 Flash

Text Model
focuses on efficiency and swift responsiveness, enabling the completion of generation tasks within minimal time
Input Tokens, 1M
From $0.30
Output Token, 1M
From $2.50

Gemini 2.5 Flash Lite

Text Model
lightweight, fast, and efficient AI model designed for speed and cost-effectiveness in everyday tasks.
Input Tokens, 1M
From $0.10
Output Token, 1M
From $0.40

Claude Sonnet 4

Text Model
high-quality text generation, multi-domain applicability, and powerful conversational interaction capabilities
Input Tokens, 1M
$3.00
Output Token, 1M
$15.00

Claude Opus 4

Text Model
most powerful AI model, renowned for its exceptional reasoning, deep analysis, and top performance on complex tasks at the frontier of AI.
Input Tokens, 1M
$15.00
Output Token, 1M
$75.00

MidJourney

Image Model
An open-source image generation model based on artificial intelligence technology, possessing outstanding text-to-image conversion capabilities.
Starting from
$0.09 / image

GPT-image-1

Image Model
Native multimodal image generation model launched in April 2025, with core functions covering image generation, editing, and variant creation.
Starting from
$40 / M tokens

Dall-E-3

Image Model
Offering improved understanding of prompts and higher quality more detailed images
Starting from
$0.04 / image

Stable Diffustion-3.5-Large

Image Model
Advanced text-to-image model, widely used in artistic creation, design, and visual content generation
Price per image
$0.06

Flux-1-schnell

Image Model
A generative model that is fast, produces high-quality images with rich details and diverse styles, and has good prompt compliance.
Price per image
$0.06

KL_Video_V1.6

Video Model
Part of the Kling AI series for video generation and processing
Starting from
$0.3 / request

HL_Video

Video Model
For converting images to videos, generating video content based on input images.
Starting from
$0.45 / request

GPT 4o Realtime

Audio Model
Real-time models available for global deployments, supporting low-latency audio interactions
Contact Sales

TTS-Azure

Audio Model
Text-to-speech services provided by Azure
From
$ 15 / M characters input

TTS-OpenAI

Audio Model
Text-to-speech services provided by OpenAI
From
$15 / M characters input

ElevenLabs

Audio Model
TTS platforms known for high-quality voice synthesis
Contact Sales

Whisper

Audio Model
Open-source automatic speech recognition model, capable of transcribing and translating speech
Price
$0.36 / hr audio input

Text-Embedding-3-Large

Embedding Model
A high-capacity pre-trained model transforms text into high-dimensional vector representations to support high-precision text similarity calculations
Price
$0.02 / M tokens

Text-Embedding-3-Small

Embedding Model
A lightweight pre-trained model is used to transform text into vectors
Price
$0.13 / M tokens
Try Hosting
Hosting your open-source models withCloudsway, benefit from optimized performanceand reduced cost

Contact Us

Your AI journey starts here.
Fill out the form and we’ll get back to you with answers.