Open weights model

Released June 2026

Nemotron 3 Ultra 550B A55B (Reasoning) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Nemotron 3 Ultra 550B A55B (Reasoning) for your use-case.

Fastest

#1
NebiusNebius
330.1 t/s
#2
CoreWeaveCoreWeave
313.3 t/s
#3
FireworksFireworks
170.3 t/s
#4
DeepInfra BF16DeepInfra BF16
118.7 t/s
#5
DeepInfraDeepInfra
102.1 t/s

Output speed

Total 8 providers

Lowest Latency

#1
CoreWeaveCoreWeave
8.27 s
#2
NebiusNebius
9.26 s
#3
FireworksFireworks
14.00 s
#4
DeepInfra BF16DeepInfra BF16
22.73 s
#5
DeepInfraDeepInfra
26.53 s

Time to first answer token

Total 8 providers

Lowest Price

#1
Blackbox AIBlackbox AI
$0.37
#2
DeepInfraDeepInfra
$0.39
#3
FireworksFireworks
$0.44
#4
Lightning AILightning AI
$0.49
#5
GMIGMI
$0.49

Blended price (per 1M tokens)

Total 8 providers

Nemotron 3 Ultra is available through 8 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For output speed, the top providers are Nebius (330.1 t/s), CoreWeave (313.3 t/s), and Fireworks (170.3 t/s). Speed varies significantly across providers, with a 223% difference between the fastest and slowest.
  • For latency, CoreWeave (8.27s), Nebius (9.26s), and Fireworks (14.00s) offer the lowest time to first answer token.
  • For pricing, Blackbox AI (0.37), DeepInfra (0.39), and Fireworks (0.44) offer the lowest blended prices per 1M tokens. Prices vary up to 3.3x across providers.

Highlights

Output tokens per second · Higher is better
Seconds · Lower is better
USD per 1M tokens (blended) · Lower is better

Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above.

Pricing

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Pricing: Blended Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended) · Lower is better

Pricing: Cache Discount

1 - (cache hit price / input price) · Higher is better

Output Speed vs. Price

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Speed

Measured by Output Speed (tokens per second)

Output Speed: Nemotron 3 Ultra 550B A55B (Reasoning)

Output speed: output tokens per second · 10,000 input tokens

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 input tokens
Most attractive quadrant
Pareto line

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token

Seconds to first token received · Lower is better · 10,000 input tokens

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Key Comparison Metrics & API Features

CoreWeave logoCoreWeave
262k
Open
$0.27
244
1.09
12.48
9.34
GMI logoGMI
262k
Open
--
--
--
--
--
DeepInfra logoDeepInfra
262k
Open
$0.47
56
6.42
55.87
40.54
DeepInfra logoDeepInfra
262k
Open
$0.92
50
8.55
63.78
45.28
Nebius logoNebius
256k
Open
$1.16
316
2.33
11.10
7.19
Lightning AI logoLightning AI
262k
Open
$0.48
--
--
--
--
Blackbox AI logoBlackbox AI
262k
Open
$0.37
--
--
--
--
Fireworks logoFireworks
262k
Open
$0.22
155
0.64
18.51
14.65

Frequently Asked Questions

Common questions about Nemotron 3 Ultra 550B A55B (Reasoning) providers