Skip to content
SambaNova

SambaNova

Inference API Provider

Reputation:
78/100
sambanova.ai

Provider Overview

Type

inference

Billing

Per token

Egress

Free

SLA Uptime

99.9%

Autoscaling

Yes

Cold Start

None

Model Pricing (8)

ModelInput $/MOutput $/MLatencyThroughputContext
llama-3.1-8bCheapest$0.10$0.100.08s1000 t/s128k
qwen-2.5-7b$0.10$0.100.06s900 t/s32k
llama-3.1-70b$0.60$0.600.15s400 t/s128k
llama-3.3-70b$0.60$0.600.12s450 t/s128k
deepseek-r1-distill-llama-70b$0.60$0.600.15s350 t/s128k
qwen-2.5-72b$0.60$0.600.15s380 t/s32k
llama-3.1-405b$2.50$2.500.3s130 t/s128k
deepseek-r1$2.00$5.001.5s100 t/s64k

Reputation Details

Pricing
70
Reliability
90
Features
75

Highlights

  • Good pricing
  • 99.9%+ SLA
  • Autoscaling supported
  • Fast cold start

Compare with Others

ProviderOverallPricingReliabilityFeaturesModels
SambaNova787090758
Together AI7870907520
Fireworks AI7870907514
Groq8690907510
DeepInfra8690907521