RunInfraby RightNow

GPUs

Measured NVIDIA GPUs for open model inference

The published catalog currently carries 2 measured GPUs across 4 published packages.

A100
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
80 GB
Bandwidth, vendor spec
2,039 GB/s
Hourly price, our rate
$2.72 per GPU-hour
Active price, our rate
$2.17 per GPU-hour
A100 40GB
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
40 GB
Bandwidth, vendor spec
Bandwidth not published.
Hourly price, our rate
$2.10 per GPU-hour
Active price, our rate
Active hourly price not published.
A10G
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
24 GB
Bandwidth, vendor spec
Bandwidth not published.
Hourly price, our rate
$1.10 per GPU-hour
Active price, our rate
Active hourly price not published.
B200
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
192 GB
Bandwidth, vendor spec
8,000 GB/s
Hourly price, our rate
$8.64 per GPU-hour
Active price, our rate
$6.84 per GPU-hour
B300
1 published package
Measured models
Kimi K3
Memory, vendor spec
288 GB HBM3e (max)
Bandwidth, vendor spec
8 TB/s (per GPU)
Hourly price, our rate
Hourly price not published.
Active price, our rate
Active hourly price not published.
H100
3 published packages
Measured models
AREX-Turbo, Qwen3.6 27B, and Qwythos-9B-Claude-Mythos-5-1M
Memory, vendor spec
80 GB
Bandwidth, vendor spec
3,350 GB/s
Hourly price, our rate
$4.18 per GPU-hour
Active price, our rate
$3.35 per GPU-hour
H200
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
141 GB
Bandwidth, vendor spec
4,800 GB/s
Hourly price, our rate
$5.58 per GPU-hour
Active price, our rate
$4.46 per GPU-hour
L4
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
24 GB
Bandwidth, vendor spec
600 GB/s
Hourly price, our rate
$0.69 per GPU-hour
Active price, our rate
$0.48 per GPU-hour
L40S
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
48 GB
Bandwidth, vendor spec
864 GB/s
Hourly price, our rate
$1.90 per GPU-hour
Active price, our rate
$1.33 per GPU-hour
T4
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
16 GB
Bandwidth, vendor spec
Bandwidth not published.
Hourly price, our rate
$0.59 per GPU-hour
Active price, our rate
Active hourly price not published.

Call Nemotron 3.5 Lightning 30B with Model APIs

Use a workspace API key and pay for input, cached input, and output tokens.

View Model APIs

TLS in transit, AES-256 at rest

Workspace isolation

No training on your data

SOC 2 Type II

GPUs

Measured NVIDIA GPUs for open model inference

The published catalog currently carries 2 measured GPUs across 4 published packages.

A100
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
80 GB
Bandwidth, vendor spec
2,039 GB/s
Hourly price, our rate
$2.72 per GPU-hour
Active price, our rate
$2.17 per GPU-hour
A100 40GB
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
40 GB
Bandwidth, vendor spec
Bandwidth not published.
Hourly price, our rate
$2.10 per GPU-hour
Active price, our rate
Active hourly price not published.
A10G
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
24 GB
Bandwidth, vendor spec
Bandwidth not published.
Hourly price, our rate
$1.10 per GPU-hour
Active price, our rate
Active hourly price not published.
B200
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
192 GB
Bandwidth, vendor spec
8,000 GB/s
Hourly price, our rate
$8.64 per GPU-hour
Active price, our rate
$6.84 per GPU-hour
B300
1 published package
Measured models
Kimi K3
Memory, vendor spec
288 GB HBM3e (max)
Bandwidth, vendor spec
8 TB/s (per GPU)
Hourly price, our rate
Hourly price not published.
Active price, our rate
Active hourly price not published.
H100
3 published packages
Measured models
AREX-Turbo, Qwen3.6 27B, and Qwythos-9B-Claude-Mythos-5-1M
Memory, vendor spec
80 GB
Bandwidth, vendor spec
3,350 GB/s
Hourly price, our rate
$4.18 per GPU-hour
Active price, our rate
$3.35 per GPU-hour
H200
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
141 GB
Bandwidth, vendor spec
4,800 GB/s
Hourly price, our rate
$5.58 per GPU-hour
Active price, our rate
$4.46 per GPU-hour
L4
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
24 GB
Bandwidth, vendor spec
600 GB/s
Hourly price, our rate
$0.69 per GPU-hour
Active price, our rate
$0.48 per GPU-hour
L40S
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
48 GB
Bandwidth, vendor spec
864 GB/s
Hourly price, our rate
$1.90 per GPU-hour
Active price, our rate
$1.33 per GPU-hour
T4
0 published packages
Measured models
Measured model names not published.
Memory, vendor spec
16 GB
Bandwidth, vendor spec
Bandwidth not published.
Hourly price, our rate
$0.59 per GPU-hour
Active price, our rate
Active hourly price not published.

Call Nemotron 3.5 Lightning 30B with Model APIs

Use a workspace API key and pay for input, cached input, and output tokens.

View Model APIs

TLS in transit, AES-256 at rest

Workspace isolation

No training on your data

SOC 2 Type II

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Call Nemotron 3.5 Lightning 30B with Model APIs

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Measured models

Call Nemotron 3.5 Lightning 30B with Model APIs