Nvidia Nemotron 3.5 Lightning 30B A3B
NVIDIA-Nemotron-3.5-Lightning-30B-A3BPricing
List prices at W&B Inference, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.07 | $0.20 | |
| Cached input 43% off input | $0.04 | 43% off input |
What it costs a month
At W&B Inference list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$33.30
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$33.60
- Coding agent1,000 requests a day, 40K in / 2K out, cached$70.80
- Overnight batch20,000 requests a day, 4K in / 0.4K out$216
Where to run it
2 hosts serve Nvidia Nemotron 3.5 Lightning 30B A3B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
W&B InferenceInference NVIDIA-Nemotron-3.5-Lightning-30B-A3B | $0.07 / $0.20 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B | |
GMI CloudInference NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | $0.15 / $1.00 +254% vs headline | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: NVIDIA Open Model LicenseRuntimes: TGI, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than W&B Inference.
Smaller NVIDIA models
No cheaper NVIDIA model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 2% less
- 2% less
- 7% less
- 12% less
Call it
Using W&B Inference's API.
from litellm import completion
response = completion(
model="wandb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Nvidia Nemotron 3.5 Lightning 30B A3B cost?
On W&B Inference, Nvidia Nemotron 3.5 Lightning 30B A3B costs $0.07 per million input tokens and $0.20 per million output tokens. Cached input costs $0.04 per million tokens.
Which APIs offer Nvidia Nemotron 3.5 Lightning 30B A3B?
Nvidia Nemotron 3.5 Lightning 30B A3B runs on 2 APIs: W&B Inference and GMI Cloud.
What is Nvidia Nemotron 3.5 Lightning 30B A3B's context window?
262K tokens, with up to 262K tokens in one reply.
Is Nvidia Nemotron 3.5 Lightning 30B A3B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Nvidia Nemotron 3.5 Lightning 30B A3B?
Models that cost less and keep most of what it can do: MiniMax M3.1 Flash on Refuseless (2% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Nvidia Nemotron 3.5 Lightning 30B A3B's API model id?
Use NVIDIA-Nemotron-3.5-Lightning-30B-A3B with W&B Inference. Other hosts use their own ids: NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 on GMI Cloud.
Sources
Raw catalog entry for NVIDIA-Nemotron-3.5-Lightning-30B-A3B on W&B Inference
{
"supports_reasoning": true,
"max_output_tokens": 262144,
"max_input_tokens": 262000,
"input_cost_per_token": 7e-8,
"output_cost_per_token": 2e-7,
"cache_read_input_token_cost": 4e-8,
"supports_prompt_caching": true,
"litellm_provider": "wandb",
"mode": "chat",
"supports_vision": false,
"source": "https://wandb.ai/site/pricing/tokens/"
}