Nyxos APIModels & Pricing
Live Model Catalog & Real-Time Pricing
Explore the live model catalog, token ratios, and per-group availability on the /pricing dashboard.
The gateway catalog evolves constantly as providers release new model versions, so this documentation never hard-codes a static list. Nyxos API publishes its live catalog at /pricing.
Exploring the Pricing Dashboard
You can inspect the entire catalog anytime without logging in:
- Live Pricing Portal: https://api.nyxos.shop/pricing
What Each Column Means
| Parameter | Description |
|---|---|
| Model Name | The exact identifier required in the model field of your API calls. Always copy it verbatim from here. |
| Vendor / Owner | Upstream provider (Anthropic, OpenAI, xAI, etc.). |
| Quota Type | Token-based: billed per input/output tokens. Per-request: fixed cost per generation (common for image and video models). |
| Model Ratio | Base cost coefficient applied to usage. |
| Completion Ratio | Extra multiplier applied to output/completion tokens (generation costs more than reading). |
| Cache Ratio | Discount factor applied to cached prompt tokens when prompt caching is supported. |
| Enabled Groups | Which token groups can call this model. With the Auto-A automatic group you get the widest coverage (see Groups & Multipliers). |
Programmatic Model Discovery via API
You can also fetch the live list of models your token can call through the standard OpenAI-compatible endpoint:
cURL
curl https://api.nyxos.shop/v1/models \
-H "Authorization: Bearer sk-YOUR_TOKEN_HERE"Python
from openai import OpenAI
client = OpenAI(
base_url="https://api.nyxos.shop/v1",
api_key="sk-YOUR_TOKEN_HERE",
)
models = client.models.list()
for model in models.data:
print(model.id)Tip: the
GET /v1/modelsresponse reflects your token's group permissions. If a model you saw on/pricingis missing here, check that your token uses theAuto-Agroup (Tokens → Edit in the panel).