Nebius

AGGREGATEDINFERENCE

N/A

Uptime

N/A

Rating

96.7%

2026-03-232026-04-21

Meta: Llama 3.1 8B Instruct341ms TTFT · 8 TPS

Qwen: Qwen2.5 Coder 7B Instruct238ms TTFT · 96 TPS

Google: Gemma 2 9B266ms TTFT · 36 TPS

Qwen: Qwen3 32B353ms TTFT · 8 TPS

Google: Gemma 3 27B527ms TTFT · 27 TPS

Qwen: Qwen3 30B A3B Instruct 2507232ms TTFT · 40 TPS

Nous: Hermes 4 70B482ms TTFT · 59 TPS

Meta: Llama 3.3 70B Instruct3834ms TTFT · 12 TPS

Qwen: Qwen3 Next 80B A3B Thinking410ms TTFT · 105 TPS

OpenAI: gpt-oss-120b390ms TTFT · 68 TPS

Prime Intellect: INTELLECT-3189ms TTFT · 128 TPS

Qwen: Qwen2.5 VL 72B Instruct818ms TTFT · 23 TPS

NVIDIA: Nemotron 3 Super1332ms TTFT · 49 TPS

NVIDIA: Llama 3.1 Nemotron Ultra 253B v1320ms TTFT · 38 TPS

Nous: Hermes 4 405B454ms TTFT · 26 TPS

Z.ai: GLM 51368ms TTFT · 39 TPS

Inference Models

Model	Input $/M	Output $/M	TTFT	TPS
Meta: Llama 3.1 8B Instruct	$0.02	$0.06	341ms	8
Qwen: Qwen2.5 Coder 7B Instruct	$0.03	$0.09	238ms	96
Google: Gemma 2 9B	$0.03	$0.09	266ms	36
Qwen: Qwen3 32B	$0.10	$0.30	353ms	8
Google: Gemma 3 27B	$0.10	$0.30	527ms	27
Qwen: Qwen3 30B A3B Instruct 2507	$0.10	$0.30	232ms	40
Nous: Hermes 4 70B	$0.13	$0.40	482ms	59
Meta: Llama 3.3 70B Instruct	$0.13	$0.40	3834ms	12
Qwen: Qwen3 Next 80B A3B Thinking	$0.15	$1.20	410ms	105
OpenAI: gpt-oss-120b	$0.15	$0.60	390ms	68
Prime Intellect: INTELLECT-3	$0.20	$1.10	189ms	128
Qwen: Qwen2.5 VL 72B Instruct	$0.25	$0.75	818ms	23
NVIDIA: Nemotron 3 Super	$0.30	$0.90	1332ms	49
MiniMax: MiniMax M2.5	$0.30	$1.20	—	—
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1	$0.60	$1.80	320ms	38
Nous: Hermes 4 405B	$1.00	$3.00	454ms	26
Z.ai: GLM 5	$1.00	$3.20	1368ms	39

4.5★★★★★(2 reviews)

clouduser42

★★★★★2025-06-15

Reliable service, great API documentation.

mlresearcher

★★★★☆2025-06-10

Good performance but support could be faster.