SambaNova Cloud

Cloud PlatformOpenAI compatible

Inference cloud built on custom RDU dataflow chips, delivering high-throughput hosting of open-weight models.

Active models

11

Families

9

Headquarters🇺🇸 Palo Alto, CA

Founded2017

API Base URL

Modelscloud.sambanova.ai/models

Model	Caps	Context	Pricing
Llama 4 Maverick 17B 128E Instruct🌍OSSLlama-4-Maverick-17B-128E-Instruct	RVTSJF	131K	$0.63$1.8
gemma-4-31B-it🌍gemma-4-31B-it		131K	$0.22$0.59
Llama 3.3 70B Instruct🌍OSSMeta-Llama-3.3-70B-Instruct	RVTSJF	131K	$0.6$1.2
Gemma 3 12B IT🌍OSSgemma-3-12b-it	RVTSJF	131K	$0.35$0.59
DeepSeek V3.2🌍OSSDeepSeek-V3.2	RVTSJF	33K	$3$4.5
DeepSeek V3.1🌍OSSDeepSeek-V3.1	RVTSJF	131K	$3$4.5
DeepSeek V3.1 (continuous batching)🌍OSSDeepSeek-V3.1-cb	RVTSJF	33K	$0.15$0.75
MiniMax M2.5🌍OSSMiniMax-M2.5	RVTSJF	164K	$0.3$1.2
DeepSeek R1 Distill Llama 70B🌍OSSDeepSeek-R1-Distill-Llama-70B	RVTSJF	33K	$0.7$1.4
GPT-OSS 120B🌍OSSgpt-oss-120b	RTSJF	131K	$0.22$0.59