NVIDIA · Released Aug 11, 2026Nemotron 3.5 Lightning 30B A3B
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads.
- Capability
- —No ECI score yet
- Input
- $0.05per 1M tokens
- Output
- $0.20per 1M tokens
- Context
- 262K262K max output
What it costs
- Input
- $0.05per million tokens
- Output
- $0.20per million tokens
- Blended (3:1)
- $0.087cheaper than 92% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.20 |
| Team assistant25M input + 5M output tokens | $2.25 |
| Production app250M input + 50M output tokens | $22.50 |
Median of 9 paid API providers on models.dev; NVIDIA also offers it free on Nvidia.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Nemotron 3.5 Lightning 30B A3B yet.
The details
- Lab
- NVIDIA
- Released
- Aug 11, 2026
- Context window
- 262,144 tokens
- Max output
- 262,144 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- Can be switched on or off
- Tool calling
- Yes
- Structured output
- Yes
- Weights
- Open weights
- API model ID
nvidia/nemotron-3.5-lightning-30b-a3bon Nvidia- Availability
- 12 API providerslisted on models.dev
What NVIDIA claims
Published by the lab at launch. Settings vary, so compare these only with care.
| Benchmark | Score | Setting | Source |
|---|---|---|---|
| MMLU-Pro | 81.94 | BF16; reasoning | Source |
| AA-Omniscience | 17.5 | BF16; reasoning | Source |
| SciCode | 32.6 | BF16; reasoning | Source |
| PinchBench | 85.37 | BF16; reasoning | Source |
| BrowseComp | 36.97 | BF16; reasoning | Source |
| AA-LCR | 52 | BF16; reasoning | Source |
| GPQA Diamond | 75.44 | BF16; reasoning; no tools | Source |
| Humanity's Last Exam | 11.72 | BF16; reasoning; no tools | Source |
| SWE-Bench Verified | 51.56 | BF16; reasoning | Source |
| SWE-Bench Multilingual | 39.33 | BF16; reasoning | Source |
| Terminal-Bench v2.1 | 24.58 | BF16; reasoning | Source |
| tau3-bench | 9.28 | BF16; reasoning; banking | Source |
More from NVIDIA
About Nemotron 3.5 Lightning 30B A3B
How much does Nemotron 3.5 Lightning 30B A3B cost?
Nemotron 3.5 Lightning 30B A3B costs $0.05 input / $0.20 output per million tokens (median across 9 API providers; free on Nvidia). At a 3:1 input-to-output mix that is $0.087 per million tokens, cheaper than 92% of the 360 priced models we track.
What is the context window of Nemotron 3.5 Lightning 30B A3B?
Nemotron 3.5 Lightning 30B A3B accepts up to 262,144 tokens per request and can write up to 262,144 tokens in one response.
How good is Nemotron 3.5 Lightning 30B A3B?
Epoch AI has not published a Capabilities Index score for Nemotron 3.5 Lightning 30B A3B yet.
Is Nemotron 3.5 Lightning 30B A3B open source?
Yes. NVIDIA publishes the weights, so it can be downloaded and self-hosted.
What inputs does Nemotron 3.5 Lightning 30B A3B support?
Nemotron 3.5 Lightning 30B A3B accepts text and replies in text. It is a reasoning model, supports tool calling and can return structured JSON output.
When was Nemotron 3.5 Lightning 30B A3B released?
NVIDIA released Nemotron 3.5 Lightning 30B A3B on Aug 11, 2026.
What are the best alternatives to Nemotron 3.5 Lightning 30B A3B?
The closest current models from other labs on capability, price and release date are Laguna XS 2.1 (Poolside, $0.06 / $0.12), Ling 3.0 Flash Fin (inclusionAI, $0.075 / $0.22), Mercury 2.5 (Inception, $0.04 / $0.15) and Gemma 4 12B IT (Google, $0.075 / $0.275).