Your next great idea.
Meet its intelligence.
Explore Qwen, GLM, Kimi and DeepSeek. Compare per-token rates and choose a model family for your application, without starting from bare metal.
Swipe the table to compare input, output and cache rates →
Small models
1 model| Model | Input | Output | Cached input | Get started |
|---|---|---|---|---|
Qwen3.8-27BQwen family | $0.21 | $1.28 | $0.043 | Request access |
Large models
4 models| Model | Input | Output | Cached input | Get started |
|---|---|---|---|---|
GLM-5.3GLM family | $0.62 | $2.16 | $0.16 | Request access |
GLM-5.3-FlashGLM family | $0.066 | $0.23 | $0.019 | Request access |
Kimi-K3Kimi family | $1.95 | $9.75 | $0.20 | Request access |
DeepSeek-V4.1-FlashDeepSeek family | $0.081 | $0.32 | $0.006 | Request access |
No models match your search. Try another name or select “All models”.
5 models in the catalog
From an idea
to your first request.
Get the integration details you need from our team, then connect your application using the assigned endpoint and model identifier.
# Use the endpoint & model ID from onboarding
curl "$ARTRUBY_BASE_URL/chat/completions" \
-H "Authorization: Bearer $ARTRUBY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "YOUR_ASSIGNED_MODEL_ID",
"messages": [{
"role": "user",
"content": "Let’s build something great."
}]
}' Illustrative integration only. Access is confirmed during onboarding; this site does not issue API keys or execute model requests.
How do I get API access?
Choose a model and select “Request access”. Share your expected traffic, use case and deployment requirements. The team will confirm availability, credentials, the base URL and exact model identifier.
How does cached-input pricing work?
Eligible cache-hit input tokens use the cached-input rate instead of the standard input rate. Cache eligibility and usage reporting are determined by the serving configuration, not by the calculator on this website.
What happens to my prompts and completions?
Please review our Data Policy for the existing inference-content and operational-metadata policies, and confirm the scope for your specific service during onboarding.
The next thing you build
starts with the right foundation.
Tell us what you’re working on. We’ll help you find the right fit.