DzRouter

Nemotron Lightning 3.5 30B A3B

ReasoningTool use

NVIDIA's hybrid Mamba-Transformer MoE model (31B total, 3B active) with a multi-token prediction speculative decoding head for low-latency serving. Tuned for high-throughput reasoning and agentic workloads.

Model id — paste this in your code
nvidia/nemotron-lightning-3.5-30b

Pricing · per 1M tokens

Show prices in
Input15 DA$0.06
Output60 DA$0.24
Cached input3 DA$0.012
Context window262KMax output: 66K

Capabilities

  • Reasoning — Thinks step by step before answering
  • Tool use — Can call your functions / tools

Estimate your cost

Estimated cost

Use this model

Create an account, top up in dinars and call it with your key:

from openai import OpenAI

client = OpenAI(
    base_url="https://dzrouter.com/v1",
    api_key="sk-dz-…",
)

reply = client.chat.completions.create(
    model="nvidia/nemotron-lightning-3.5-30b",
    messages=[{"role": "user", "content": "Salam!"}],
)
print(reply.choices[0].message.content)
Create a free account

Start building with AI today

Create your account, top up from 500 DA and send your first request in minutes.

Create a free account