One API · Open & frontier models
Find your model.
Build your next idea.
Compare AI models in chat, then bring them into your app with one OpenAI-compatible API.
639Models in the live catalog
3API protocols
1Unified endpoint
PythonSyntax highlighted
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.clssai.com/v1",
api_key=os.environ["CLSSAI_API_KEY"],
)
response = client.chat.completions.create(
model="stealth/space-bunny-alpha",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)ONE API · MANY PROVIDERS
UNIFIED CATALOG
One API for every model
Models, capabilities, context, and prices in one place. Works with the OpenAI SDK.
Browse the full catalogRELIABILITY
Provider-aware routing
Explore model publishers, then inspect hosting endpoints and reference performance on each model page.
View providersSUCCESS POLICY
Compatibility that stays visible
Understand supported request parameters and the fields the gateway passes through or transforms.
Read the parameters guideOBSERVABILITY
Know what actually happened
Understand response usage, request costs, key balances and asynchronous settlement.
Understand usage and costSTART HERE
Featured models
Popular models available through CLSSAI. Reference prices from CLSSAI catalog; missing values are shown as —.
Space Bunny Alpha
by stealth
Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support. It delivers adjustable reasoning effort, and a 1M-token context window. Space...
1M context$0/M input$0/M output
DeepSeek: DeepSeek V4.1 Flash
by deepseek
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
1.05M context$0.3/M input$1.2/M output
Z.ai: GLM 5.3 Flash
by z-ai
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
1.05M context$0.15/M input$0.5/M output
QUICKSTART
From zero to first response
TRANSPARENT BY DEFAULT
Fewer blockers should not mean invisible rules.
Open-model priority, filterable data policies, and optional request enhancement keep success optimization under your control.
- Published prices shown by default
- Request metadata only by default
- Explicit models are never silently replaced