Providers· Inference host· 7 tracked models

SambaNova — pricing & performance

Compare models All providers Data sources

Models served

of 1,094 tracked models

Mean output speed

130

tokens per second, averaged over
7 measured endpoints

Mean latency

1.3s

time to first token, averaged over
7 measured endpoints

Cheapest blended

$0.34

per 1M tokens at a 3:1
input:output blend

Output speed on SambaNova

Output tokens per second for all 7 models on SambaNova with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 7 of 7 models⇩

319

231

143

Llama 3.3 70B
Instruct

The Known Good

7 models on SambaNova

Full leaderboard →

Model	Creator	Input $/M	Output $/M	Blended	Speed	TTFT	Context
DeepSeek: DeepSeek V3.1	DeepSeek	$0.65	$1.50	$0.86	82	1.3s	131k
DeepSeek: DeepSeek V3.2	DeepSeek	$3.00	$4.50	$3.38	32	3.2s	33k
Google: Gemma 4 31B	Google	$0.38	$1.15	$0.57	79	1.5s	131k
Meta: Llama 3.3 70B Instruct	Meta	$0.45	$0.90	$0.56	25	0.4s	131k
MiniMax: MiniMax M2.7	MiniMax	$0.60	$2.40	$1.05	231	1.1s	197k
MiniMax: MiniMax M3	MiniMax	$0.60	$2.40	$1.05	143	1.0s	1.05M
OpenAI: gpt-oss-120b	OpenAI	$0.14	$0.95	$0.34	319	0.5s	131k

The Known Good

Source. Prices, endpoint availability and throughput for SambaNova are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.