Nemotron 3.5 Lightning 30B A3B Official Specifications, Pricing & Benchmarks
Nemotron 3.5 Lightning 30B A3B (nemotron-3.5-lightning) by NVIDIA, released 2026-08-11, featuring 1,048,576 context window, 235,929 max output tokens, and Text input.
📋 Nemotron 3.5 Lightning 30B A3B Official API & System Card Specifications
Verified against official NVIDIA developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- nemotron-3.5-lightning
- Release Date
- 2026-08-11
- Weight License
- Open-Weight (API Spec)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 1,049,000 tokens (1049K)
- Max Output Tokens
- 235,929 tokens
- Input Modalities
- Text
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Open-Weight + Cloud API
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 0.07
- Cached Input / 1M
- $ 0.04 -43%
- Output / 1M Tokens
- $ 0.2
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Nemotron 3.5 Lightning 30B A3B Full Benchmark Scorecard
13 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 5 items
PinchBench evaluates coding agents on real-world agentic coding tasks, measuring both best-case and average performance across complex software engineering scenarios.
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++.
SciCode is a research coding benchmark curated by scientists that challenges language models to code solutions for scientific problems.
Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.
🤖 Agents & Tools 2 items
BrowseComp is a benchmark comprising 1,266 questions that challenge AI agents to persistently navigate the internet in search of hard-to-find, entangled information.
τ³-Bench banking domain evaluates agentic models on multi-turn, tool-using customer-support scenarios in a simulated retail banking environment.
📐 Math 2 items
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions.
📜 Long Context 1 items
🧠 Reasoning & Science 2 items
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
OmniScience is a broad scientific knowledge and reasoning benchmark that measures both answer accuracy and non-hallucination (calibrated abstention) across science domains.
📚 Knowledge & General 1 items
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Nemotron 3.5 Lightning 30B A3B
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Nemotron 3.5 Lightning 30B A3B open-source or proprietary?
Nemotron 3.5 Lightning 30B A3B (nemotron-3.5-lightning) is a proprietary commercial model by NVIDIA. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Nemotron 3.5 Lightning 30B A3B?
Nemotron 3.5 Lightning 30B A3B supports 1049K input context and 235,929 max output tokens, priced at $0.07/1M input ($0.04/1M cached) and $0.2/1M output.