Model Details
Owner
NVIDIA
Released
Aug 11, 2026
Status
Active
Context Length
1,048,576
Max Output
NA
Provider
Perplexity
Where is nemotron-3.5-lightning-30b-a3b a perfect fit?
NVIDIA Nemotron 3.5 Lightning 30B A3B is a 30B-parameter MoE reasoning model with only 3B active parameters, designed specifically as a high-speed workhorse for long-running autonomous agents, sub-agents, and agentic workflows.
- Long-running autonomous AI agents
- Sub-agent and multi-agent workloads
- Coding and software engineering
- Tool-using agentic workflows
- RAG and knowledge-intensive applications
- Long-context document analysis
- Structured output and function calling
- High-throughput reasoning applications
- Long-running autonomous AI agents
- Sub-agent and multi-agent workloads
- Coding and software engineering
- Tool-using agentic workflows
- RAG and knowledge-intensive applications
- Long-context document analysis
- Structured output and function calling
- High-throughput reasoning applications
Quick Model Estimate
Your GPT-5 Cost Estimate
💰 Total Cost
USD 3.00
for 1000 input + 1000 output tokens
📥 Input (1000 × $0.011500)
USD 1.5000
📤 Output (1000 × $0.170000)
USD 1.5000
Cost Breakdown
📥 Input 50%
📤 Output 50%
Prices updated daily from official provider data.
Pricing
|
Provider
↕
|
Modality
↕
|
Tier
↕
|
Input Price
(per 1M tokens) ↕ |
Output Price
(per 1M tokens) ↕ |
Context Size
↕
|
View
|
|---|---|---|---|---|---|---|
 Perplexity
|
Text | Standard | $0.0115 | $0.1700 | 1,048,576 tokens | → |