•

Open weights model

•

Released August 2026

Nemotron 3.5 Lightning API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Nemotron 3.5 Lightning for your use-case.

Lowest Time per Task

#1
PrimaLabs (NVFP4)PrimaLabs (NVFP4)
2.8 min
#2
DeepInfra (NVFP4)DeepInfra (NVFP4)
3.3 min
#3
CoreWeave (BF16)CoreWeave (BF16)
4.0 min
#4
Crusoe (BF16)Crusoe (BF16)
4.1 min
#5
Nebius (BF16)Nebius (BF16)
5.9 min

Time per Intelligence Index task (minutes)

Total 5 providers

Lowest Cost per Task

#1
CoreWeave (BF16)CoreWeave (BF16)
$0.24
#2
Crusoe (BF16)Crusoe (BF16)
$0.26
#3
DeepInfra (NVFP4)DeepInfra (NVFP4)
$0.31
#4
Nebius (BF16)Nebius (BF16)
$0.32
#5
PrimaLabs (NVFP4)PrimaLabs (NVFP4)
$0.55

Cost per Intelligence Index task

Total 5 providers

Nemotron 3.5 Lightning is available through 5 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For time per task, PrimaLabs (NVFP4) (2.8 min), DeepInfra (NVFP4) (3.3 min), and CoreWeave (BF16) (4.0 min) finish an Intelligence Index task fastest.
  • For cost per task, CoreWeave (BF16) ($0.24), Crusoe (BF16) ($0.26), and DeepInfra (NVFP4) ($0.31) are the cheapest per Intelligence Index task. Cost varies up to 2.3x across providers.
Inference time (minutes) per Intelligence Index task · Lower is better
Weighted average cost (USD) per Intelligence Index task · Lower is better

Pricing

Cost per Intelligence Index Task: Nemotron 3.5 Lightning

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Pricing: Cache Hit, Input, and Output: Nemotron 3.5 Lightning

Price (USD per M Tokens) · Lower is better

Output Speed vs. Cost per Task: Nemotron 3.5 Lightning

Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task
Most attractive quadrant
Pareto line

Speed

Average of the single-request and multi-turn agentic workloads measured

Time per Intelligence Index Task: Nemotron 3.5 Lightning

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Lower is better

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token: Nemotron 3.5 Lightning

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate: Nemotron 3.5 Lightning

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

Caching

Cache Hit Rate: Nemotron 3.5 Lightning

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

Cost per Task vs. Cache Hit Rate: Nemotron 3.5 Lightning

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026
Most attractive quadrant

Key Comparison Metrics & API Features

CoreWeave logoCoreWeave
$0.24
4.0
10.49
4.5%
262k
Open
Crusoe logoCrusoe
$0.26
4.1
18.65
0.0%
262k
Open
DeepInfra logoDeepInfra
$0.31
3.3
9.84
0.0%
262k
Open
Nebius logoNebius
$0.32
5.9
18.92
0.0%
1M
Open
PrimaLabs logoPrimaLabs
$0.55
2.8
5.79
0.0%
1M
Open

Frequently Asked Questions

Common questions about Nemotron 3.5 Lightning providers