impulse

Nemotron Lightning 3.5 30B A3B

Open weights
API id nemotron-lightning-3p5-30b-a3b
Input / 1M
$0.05
at Fireworks AI
Output / 1M
$0.20
at Fireworks AI
Context window
262K
tokens
Max output
33K
tokens per reply
Hosts
1
2 listings
Released
-
date not published

Pricing

List prices at Fireworks AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.05$0.20
Cached input
80% off input
$0.01
Priority
25% more
$0.0625$0.25

What it costs a month

At Fireworks AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$26.40
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$21.60
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$38.40
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$168
Use your own numbers

Where to run it

1 host serve Nemotron Lightning 3.5 30B A3B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Fireworks AIInference
nemotron-lightning-3p5-30b-a3b
$0.05 / $0.20
Show 1 more listings: regions, snapshots and variants
Fireworks AI
Alias
nemotron-lightning-3p5-30b-a3b
$0.05 / $0.20

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
Open weights
License: NVIDIA Open Model License
Runtimes: 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 Fireworks AI.

Smaller NVIDIA models

No cheaper NVIDIA model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

Model line

Newer and older versions, at each lab's own price.

  1. UndatedNemotron 3.5 Lightning 30B A3BLatest$0.0115 / $0.17
  2. UndatedNemotron Lightning 3.5 30B A3BThis page$0.05 / $0.20

Call it

Using Fireworks AI's API.

Python
from litellm import completion

response = completion(
    model="fireworks_ai/nemotron-lightning-3p5-30b-a3b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nemotron Lightning 3.5 30B A3B cost?

On Fireworks AI, Nemotron Lightning 3.5 30B A3B costs $0.05 per million input tokens and $0.20 per million output tokens. Cached input costs $0.01 per million tokens.

Which APIs offer Nemotron Lightning 3.5 30B A3B?

Nemotron Lightning 3.5 30B A3B runs on 1 API: Fireworks AI.

What is Nemotron Lightning 3.5 30B A3B's context window?

262K tokens, with up to 33K tokens in one reply.

Is Nemotron Lightning 3.5 30B A3B being retired?

It has been retired: Fireworks AI retired it on 7 Nov 2026.

Is there a newer version of Nemotron Lightning 3.5 30B A3B?

Yes. Nemotron 3.5 Lightning 30B A3B is the newest model in this line.

What are cheaper alternatives to Nemotron Lightning 3.5 30B A3B?

Models that cost less and keep most of what it can do: DeepSeek V4.1 Flash Fast on Refuseless (14% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Nemotron Lightning 3.5 30B A3B's API model id?

Use nemotron-lightning-3p5-30b-a3b with Fireworks AI.

Sources

Raw catalog entry for nemotron-lightning-3p5-30b-a3b on Fireworks AI
{
  "cache_read_input_token_cost": 1e-8,
  "cache_read_input_token_cost_priority": 1.25e-8,
  "deprecation_date": "2026-11-07",
  "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md",
  "input_cost_per_token": 5e-8,
  "input_cost_per_token_priority": 6.25e-8,
  "litellm_provider": "fireworks_ai",
  "max_input_tokens": 262144,
  "max_output_tokens": 32768,
  "mode": "chat",
  "output_cost_per_token": 2e-7,
  "output_cost_per_token_priority": 2.5e-7,
  "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
  "successor_model": "Nemotron Super VL",
  "supports_function_calling": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": false
}