PrimaLabs models

0 models in this catalog are created by PrimaLabs; 1 additional models are available through its hosting offerings. The newest dated release listed is DeepSeek V4.1 Flash 1017 (Oct 17, 2026).

Updated: Nov 5, 2026Data as of: Nov 2, 2026

Visit PrimaLabs

Compare hosting providers

DeepSeek V4.1 Flash 1017(max)

Token cost

USD per 1M tokens, 50% input + 50% output. Lower is better.

$0.2
DeepInfra
$0.36
Bitdeer AI
$0.38
LithosAI
$0.38
SiliconFlow
$0.38
Wafer
$0.45
GMI
$0.6
PrimaLabs
$0.63
Modal
$0.67
Makora
$0.75
Baseten
$0.75
DeepSeek
$0.75
DigitalOcean
$0.75
Fireworks
$0.75
Nebius
$0.75
Novita
$0.75
Parasail
$0.75
Systalyze
$0.75
Together AI

Output speed

Tokens per second. Higher is better.

845.4 tok/s
Systalyze
391.09 tok/s
Nebius
382.94 tok/s
Together AI
363.7 tok/s
GMI
294.28 tok/s
Bitdeer AI
253.96 tok/s
DigitalOcean
248.98 tok/s
LithosAI
243.15 tok/s
Parasail
233.59 tok/s
Modal
231.3 tok/s
SiliconFlow
225.04 tok/s
PrimaLabs
214.83 tok/s
Fireworks
211.52 tok/s
Makora
205.72 tok/s
Wafer
173.21 tok/s
DeepSeek
166.81 tok/s
Baseten
149.88 tok/s
Novita
92.09 tok/s
DeepInfra

Time to first token

Seconds until the first token. Lower is better.

0.31 s
Together AI
0.35 s
Baseten
0.5 s
DigitalOcean
0.6 s
Modal
0.62 s
Wafer
0.62 s
Parasail
0.7 s
DeepInfra
0.8 s
PrimaLabs
0.94 s
Makora
0.96 s
LithosAI
0.99 s
Systalyze
1.16 s
SiliconFlow
1.28 s
DeepSeek
1.33 s
Nebius
1.34 s
Fireworks
1.45 s
GMI
1.62 s
Novita
1.65 s
Bitdeer AI

All models

1 models

All PrimaLabs models in the dataset, newest reported release dates first.
Model	Date released	Model details
DeepSeek V4.1 Flash 1017	Oct 17, 2026	View model