
Unified AI gateway
Leading AI models. One API.
Create with image, video, audio, and chat models. Compare prices, try a model, and connect it to your product.
Model market
Choose the right model for the job
Compare modalities and public usage prices without learning a different integration for every provider.

qwen-image-edit-2509
Qwen · Text to image
$0.0019/ image
Official
doubao-seedream-3-0-t2i-250415
ByteDance · Text to image
$0.0090/ image
Official
Grok Imagine Image 2.0
xAI · Text to image
$0.0238/ image
Official
doubao-seedream-4-0-250828
ByteDance · Text to image
$0.0180/ image
Official
Wan2.7 Image
Alibaba · Text to image
$0.0217/ image
Official
Wan2.7 Image Pro
Alibaba · Text to image
$0.0542/ image
Official
Qwen Image 3.0
Qwen · Text to image
$0.0240/ image
Official
Nano Banana 2.1
Google · Text to image
$0.0114/ image
OfficialCurrent pricing
Below official pricing
Models currently priced below the provider’s official list price.
gemini-3-flash-preview
Google · Chat
Text generation for writing, questions and summaries. Try the verified short-copy example.
$0.0441 in · $0.2647 out/ 1M
Officialgemini-3.1-flash-lite-preview
Google · Chat
Generate content through the unified API.
$0.0221 in · $0.1324 out/ 1M
Officialgemini-3.7-flash
Google · Chat
Text generation for writing, questions and summaries. Try the verified short-copy example.
$0.0662 in · $0.3309 out/ 1M
OfficialGemini 3.8 Flash
Google · Chat
Text generation for questions, writing and summaries, with streaming replies.
$0.0662 in · $0.3309 out/ 1M
OfficialGemini 4 Argon
Google · Chat
Text generation for questions, writing and summaries, with streaming replies.
$0.1765 in · $0.8824 out/ 1M
Officialclaude-haiku-4-5-20251001
Anthropic · Chat
Text generation for writing, questions and summaries. Try the verified short-copy example.
$0.1059 in · $0.5294 out/ 1M
Officialclaude-opus-4-1-20250805
Anthropic · Chat
Generate content through the unified API.
$1.5883 in · $7.9416 out/ 1M
Officialclaude-opus-4-5-20251101
Anthropic · Chat
Text generation for writing, questions and summaries. Try the verified short-copy example.
$0.5294 in · $2.6472 out/ 1M
OfficialEstimated comparisons are approximate and depend on the stated specifications. Check model details for the source.
- models available
- 241
- model types
- 6
- API key for every model
- 1
- monthly subscription
- $0
Featured models from
Anthropic
Google
Zhipu
xAI
Moonshot
MiniMax
ByteDance
Qwen
Alibaba
HappyHorse
BUILT FOR YOUR WORKFLOW
From model access to product delivery.
Models, keys, generation tasks, and usage records. One connected workflow.
The right model for every task
Compare capabilities and prices across reasoning and creative models. Explore parameters and try models on their detail pages.
Explore the catalogKnow what every call costs
Public prices by model and billing unit. Match usage to charge records in your console.
A separate key for each application
Manage API keys and usage limits for a clearer view of your applications.
Long-running jobs. Clear progress.
Track image, video, and audio generation through task status and retrieve the finished result.
BUILD SOMETHING REAL
Take your next idea into production.
Start with a real use case and follow a complete integration guide.
AI artwork
Coastal fashion editorial
Browse image models
AI artwork
Canyon road, cinematic
Browse video models
AI artwork
Botanical fragrance still life
Browse image models
AI artwork
Paper-craft moon observatory
Browse image models
AI artwork
Orbital expedition, sci-fi
Browse video models
AI artwork
Sunlit residence interior
Browse image models

Add image creation to your app
Turn a prompt into an image and connect generation to your creative workflow.
Read integration guide
Turn ideas into video content
Submit a task, track progress, and retrieve the output in one complete workflow.
Read integration guideBuild an assistant for your product
Keep the familiar OpenAI SDK and bring conversations into your application.
Read integration guideIntegration
From API key to first response in three steps
- 01
Create an API key
Create a key from your workspace and set the limits your application needs.
sk-••••••••••••••••Create a key - 02
Use the familiar SDK
Keep the OpenAI SDK and point its base URL to the Orux endpoint.
base_url = "https://orux.top/api/v1"Read the quickstart - 03
Choose a model
Use the model alias shown in the catalog. Check each model page for its input format, endpoint, and price before you connect.
model = "claude-fable-5"Browse models
A stable interface, not another SDK
The same authentication and request pattern works across all models. Async generation tasks use a consistent task lifecycle.
curl https://orux.top/api/v1/chat/completions \
-H "Authorization: Bearer $ORUX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-fable-5",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Replace $ORUX_API_KEY with your own key. Each model page lists its parameters and price.
CLEAR PRICING
Understand the price. Then build.
Chat, images, video, and audio have different billing units. Compare model specifications and public prices to find the right fit.
See all pricingChat models
Separate input and output rates
Image models
Check per-image or per-task pricing
Video & audio
Check duration or task billing per model
Everything you need before you connect.
FAQ
Common questions
Can I keep using the OpenAI SDK?+
Yes. Set the Orux base URL and API key, then select an available model alias. Provider-specific capabilities remain documented on each model page.
Which model types are supported?+
The gateway covers chat, image, video, and audio. Synchronous and asynchronous workloads use the endpoint pattern appropriate to each modality.
How is usage billed?+
Every model lists a public price in Credits for its billing unit, such as per image, per second of video, per track, or per volume of text. 1 USD = 200 Credits. Your usage and charge records stay visible in the workspace.
Build against one API, not a collection of vendors
Create a workspace, issue a scoped API key, and test your first model from the market.
