All promotions
GuidesMCP

SambaNova

Inference providerUS Westprices checked Oct 23, 06:00 UTC

Pricing page ↗

SambaNova serves 7 models at a verified price. On the 7 it shares with other hosts, it is never the cheapest and charges a median 221% above it.

Models served77 with open weights
Cheapest input, per M$0.14gpt-oss-120b
Uptime, last 24 h87.8%average of its 7 OpenRouter endpoints
Sign-upno free credits stated
Newest first
ModelPrecisionContextToolsInputOutputCache
MiniMax-M3not stated by the host1M✓$0.60$2.40$0.06
Gemma 4 31Bnot stated by the host128K✓$0.38$1.15—
MiniMax M2.7not checked yet200K—$0.60$2.40$0.06
DeepSeek V3.2not stated by the host32K—$3.00$4.50—
DeepSeek V3.1fp8128K✓$0.65$1.50—
gpt-oss-120bnot stated by the host128K✓$0.14$0.95—
Llama 3.3 70Bnot stated by the host128K—$0.45$0.90—

7 of 7 models · prices per million tokens · precision and context: read at SambaNova's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as SambaNova declares them to OpenRouter

ConditionWhat it saysSource
Sign-upCard requireddocs.sambanova.ai
Free creditsNone stated—
Headquarters regionUS West—
Price listWhere its per-token prices are publishedcloud.sambanova.ai
API documentationIts own docsdocs.sambanova.ai
Status pageOutages and incidents, as SambaNova reports themstatus.sambanova.ai
Terms of serviceIts termssambanova.ai

Links checked Oct 8.