SambaNova API pricing

Hosted9 language models

As of Oct 14, 2026, SambaNova lists 9 language models through its API. Its cheapest language model is gpt-oss-120b at $0.22 input / $0.59 output per million tokens.

Language models (9)

Prices per million tokens.

Model	Input	Output	Cached input	Context
DeepSeek R1 sambanova/DeepSeek-R1	$5.00	$7.00	—	33K
DeepSeek V3.1 sambanova/DeepSeek-V3.1	$3.00	$4.50	—	131K
DeepSeek V3.2 sambanova/DeepSeek-V3.2	$3.00	$4.50	—	33K
Gemma 4 31B IT sambanova/gemma-4-31B-it	$0.38	$1.15	—	131K
gpt-oss-120b sambanova/gpt-oss-120b	$0.22	$0.59	—	131K
MiniMax M2.7 sambanova/MiniMax-M2.7	$0.60	$2.40	—	197K
MiniMax M3 MiniMax-M3	$0.60	$2.40	$0.06	1.05M
Llama 4 Maverick 17B 128e Instruct sambanova/Llama-4-Maverick-17B-128E-Instruct	$0.63	$1.80	—	131K
Meta Llama 3.3 70B Instruct sambanova/Meta-Llama-3.3-70B-Instruct	$0.60	$1.20	—	131K

DeepSeek R1
sambanova/DeepSeek-R1
Input
$5.00
Output
$7.00
Context
33K
DeepSeek V3.1
sambanova/DeepSeek-V3.1
Input
$3.00
Output
$4.50
Context
131K
DeepSeek V3.2
sambanova/DeepSeek-V3.2
Input
$3.00
Output
$4.50
Context
33K
Gemma 4 31B IT
sambanova/gemma-4-31B-it
Input
$0.38
Output
$1.15
Context
131K
gpt-oss-120b
sambanova/gpt-oss-120b
Input
$0.22
Output
$0.59
Context
131K
MiniMax M2.7
sambanova/MiniMax-M2.7
Input
$0.60
Output
$2.40
Context
197K
MiniMax M3
MiniMax-M3
Input
$0.60
Output
$2.40
Context
1.05M
Llama 4 Maverick 17B 128e Instruct
sambanova/Llama-4-Maverick-17B-128E-Instruct
Input
$0.63
Output
$1.80
Context
131K
Meta Llama 3.3 70B Instruct
sambanova/Meta-Llama-3.3-70B-Instruct
Input
$0.60
Output
$1.20
Context
131K

Prices in USD from LiteLLM and models.dev, checked daily; confirm on SambaNova's pricing page before you rely on a number.