LIVE
Models: —+Providers: —+Cheapest H100: $2.49/hrUpdated: 05:17 PMModels: —+Providers: —+Cheapest H100: $2.49/hrUpdated: 05:17 PM
Marketplace
Providers Models
S

SambaNova

AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating

30-Day Uptime

100%
2026-03-232026-04-21

Inference Latency

OpenAI: gpt-oss-120b1255ms TTFT · 231 TPS
DeepSeek: DeepSeek V3.12446ms TTFT · 11 TPS
MiniMax: MiniMax M2.51611ms TTFT · 120 TPS
Google: Gemma 3 12B1314ms TTFT · 64 TPS
Meta: Llama 3.3 70B Instruct3003ms TTFT · 23 TPS
Meta: Llama 3.3 70B Instruct2641ms TTFT · 23 TPS
Meta: Llama 4 Maverick1544ms TTFT · 116 TPS
DeepSeek: DeepSeek V3.13461ms TTFT · 25 TPS

Inference Models

ModelInput $/MOutput $/MTTFTTPS
OpenAI: gpt-oss-120b$0.14$0.951255ms231
DeepSeek: DeepSeek V3.1$0.15$0.752446ms11
MiniMax: MiniMax M2.5$0.22$0.591611ms120
Google: Gemma 3 12B$0.22$0.591314ms64
Meta: Llama 3.3 70B Instruct$0.45$0.903003ms23
Meta: Llama 3.3 70B Instruct$0.60$1.202641ms23
Meta: Llama 4 Maverick$0.63$1.801544ms116
DeepSeek: DeepSeek V3.1$0.65$1.503461ms25

Community Reviews

4.5★★★★★(2 reviews)
clouduser42
★★★★★2025-06-15

Reliable service, great API documentation.

mlresearcher
★★★★2025-06-10

Good performance but support could be faster.

SambaNova — Provider Scorecard — NexusGPU | NexusGPU