•

Open weights model

•

Released October 2026

Nemotron 3.5 Super VL API Provider Benchmarking & Analysis

Model Comparison

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

Lowest Time per Task

#1
BasetenBaseten
2.7 min
#2
CoreWeave (NVFP4)CoreWeave (NVFP4)
2.9 min
#3
DeepInfraDeepInfra
4.0 min
#4
PrimaLabs (NVFP4)PrimaLabs (NVFP4)
4.1 min
#5
Together AI (NVFP4)Together AI (NVFP4)
4.7 min

Time per Intelligence Index task (minutes)

Total 9 providers

Lowest Cost per Task

#1
BasetenBaseten
$0.31
#2
DeepInfraDeepInfra
$0.35
#3
PrimaLabs (NVFP4)PrimaLabs (NVFP4)
$0.45
#4
CoreWeave (NVFP4)CoreWeave (NVFP4)
$0.47
#5
CrusoeCrusoe
$0.52

Cost per Intelligence Index task

Total 9 providers

Nemotron 3.5 Super VL is available through 9 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For time per task, Baseten (2.7 min), CoreWeave (NVFP4) (2.9 min), and DeepInfra (4.0 min) finish an Intelligence Index task fastest.
  • For cost per task, Baseten ($0.31), DeepInfra ($0.35), and PrimaLabs (NVFP4) ($0.45) are the cheapest per Intelligence Index task. Cost varies up to 3.0x across providers.
  • Baseten is both the quickest and the cheapest per task.
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 Super VL

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

Pricing: Cache Hit, Input, and Output: Nemotron 3.5 Super VL

Price (USD per M Tokens) · Lower is better

Output Speed vs. Cost per Task: Nemotron 3.5 Super VL

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

Speed

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

Time per Intelligence Index Task: Nemotron 3.5 Super VL

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 Super VL

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 Super VL

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 Super VL

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 Super VL

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

Key Comparison Metrics & API Features

Baseten logoBaseten
$0.31
2.7
6.20
0.0%
1M
Open
Bitdeer AI logoBitdeer AI
$0.53
7.8
16.58
1.6%
1M
Open
CoreWeave logoCoreWeave
$0.47
3.0
7.13
0.0%
1M
Open
Crusoe logoCrusoe
$0.52
15.8
32.21
13.5%
262k
Open
DeepInfra logoDeepInfra
$0.35
4.9
13.32
0.0%
1M
Open
DigitalOcean logoDigitalOcean
$0.94
9.1
18.55
0.0%
131k
Open
Nebius logoNebius
$0.84
8.4
15.84
3.0%
1M
Open
PrimaLabs logoPrimaLabs
$0.45
4.0
10.07
0.0%
1M
Open
Together AI logoTogether AI
$0.61
4.6
11.69
0.0%
262k
Open

Frequently Asked Questions

Common questions about Nemotron 3.5 Super VL providers