Available models
| Model ID | Provider | Parameters | Context | Speed | Best For |
|---|
nemotron-3-super | NVIDIA | 120B (MoE, 12B active) | 131K | Fast | General, efficient |
step-3.5-flash | StepFun | — | 131K | Medium | General |
glm-4.5-air | Zhipu AI | — | 131K | Medium | General, multilingual |
Nemotron 3 Super
NVIDIA’s Nemotron 3 Super is a 120B MoE model with only 12B active parameters — fast inference with strong quality. Good for general tasks where you want a balance of speed and intelligence.
Step 3.5 Flash
StepFun’s Step 3.5 Flash is a general-purpose model. Note: does not support tool calling — use a different model if you need function calling.
GLM 4.5 Air
Zhipu AI’s GLM 4.5 Air is a general-purpose multilingual model with strong Chinese language capabilities.
Code example
from openai import OpenAI
client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")
response = client.chat.completions.create(
model="nemotron-3-super",
messages=[{"role": "user", "content": "Summarize this article: ..."}]
)
step-3.5-flash does not support tool calling / function calling. All other models on Kyma support tools.
