SambaNova

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by SambaNova

Model name

9 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V3.1 FP8 deepseek-ai/DeepSeek-V3.1:sambanova	131k	$0.68/M	$1.57/M	N/A	2.9s	85 tps
DeepSeek V3.2 deepseek/deepseek-v3.2:sambanova	33k	$3.15/M	$4.72/M	N/A	3.7s	50.5 tps
DeepSeek V3.2 (Thinking) deepseek/deepseek-v3.2:thinking:sambanova	33k	$3.15/M	$4.73/M	N/A	3.7s	50.5 tps
Gemma 4 31B google/gemma-4-31b-it:sambanova	131k	$0.40/M	$1.21/M	N/A	3.4s	63 tps
Gemma 4 31B (Thinking) google/gemma-4-31b-it:thinking:sambanova	131k	$0.40/M	$1.21/M	N/A	3.4s	63 tps
GPT OSS 120B openai/gpt-oss-120b:sambanova	131k	$0.15/M	$1.00/M	N/A	1s	396 tps
Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct:sambanova	131k	$0.47/M	$0.94/M	N/A	0.6s	127 tps
MiniMax M3 minimax/minimax-m3:sambanova	1.0M	$0.63/M	$2.52/M	$0.06/M	1.9s	102 tps
MiniMax M3 Thinking minimax/minimax-m3:thinking:sambanova	1.0M	$0.63/M	$2.52/M	$0.06/M	1.9s	102 tps

DeepSeek V3.1

FP8

deepseek-ai/DeepSeek-V3.1:sambanova

Context

131k

Input /M

$0.68/M

Output /M

$1.57/M

Cache read /M

N/A

TTFT

2.9s

Throughput

85 tps

DeepSeek V3.2

deepseek/deepseek-v3.2:sambanova

Context

33k

Input /M

$3.15/M

Output /M

$4.72/M

Cache read /M

N/A

TTFT

3.7s

Throughput

50.5 tps

DeepSeek V3.2 (Thinking)

deepseek/deepseek-v3.2:thinking:sambanova

Context

33k

Input /M

$3.15/M

Output /M

$4.73/M

Cache read /M

N/A

TTFT

3.7s

Throughput

50.5 tps

Gemma 4 31B

google/gemma-4-31b-it:sambanova

Context

131k

Input /M

$0.40/M

Output /M

$1.21/M

Cache read /M

N/A

TTFT

3.4s

Throughput

63 tps

Gemma 4 31B (Thinking)

google/gemma-4-31b-it:thinking:sambanova

Context

131k

Input /M

$0.40/M

Output /M

$1.21/M

Cache read /M

N/A

TTFT

3.4s

Throughput

63 tps

GPT OSS 120B

openai/gpt-oss-120b:sambanova

Context

131k

Input /M

$0.15/M

Output /M

$1.00/M

Cache read /M

N/A

TTFT

1s

Throughput

396 tps

Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct:sambanova

Context

131k

Input /M

$0.47/M

Output /M

$0.94/M

Cache read /M

N/A

TTFT

0.6s

Throughput

127 tps

MiniMax M3

minimax/minimax-m3:sambanova

Context

1.0M

Input /M

$0.63/M

Output /M

$2.52/M

Cache read /M

$0.06/M

TTFT

1.9s

Throughput

102 tps

MiniMax M3 Thinking

minimax/minimax-m3:thinking:sambanova

Context

1.0M

Input /M

$0.63/M

Output /M

$2.52/M

Cache read /M

$0.06/M

TTFT

1.9s

Throughput

102 tps

Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using SambaNova via the API

Call a model served by SambaNova using its displayed model ID, including the provider suffix when selection is supported.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V3.1:sambanova",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :sambanova to the model ID, set "provider": "sambanova" in the request body, or send an X-Provider: sambanova header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

SambaNova offers multiple service lanes, each pinned with its own id: sambanova, sambanova-high-throughput (High Throughput). The table shows which lane serves each row.

See the API documentation for provider preferences, price-aware routing, and error behavior.