DeepSeek V3.2 API pricing on SambaNova
Every SambaNova DeepSeek V3.2 rate we track, compared against 10 providers serving the same model.
The cheapest DeepSeek V3.2 input price we currently track is $0.209/1M on GMI Cloud.
SambaNova DeepSeek V3.2 rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $3.00/1M | $4.50/1M |
About DeepSeek V3.2
- Creator
- DeepSeek
- Modalities
- text
DeepSeek V3.2 on other providers
About SambaNova
SambaNova builds its own AI accelerator, the Reconfigurable Dataflow Unit (RDU), and runs SambaNova Cloud, an OpenAI-compatible inference API for open models served on that hardware and billed per token.
Frequently Asked Questions
How much does DeepSeek V3.2 cost on SambaNova?
SambaNova serves DeepSeek V3.2 from $3.00 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.
Is SambaNova the cheapest way to run DeepSeek V3.2?
SambaNova ranks #10 of 10 providers we track serving DeepSeek V3.2. The cheapest input price right now is on GMI Cloud. Price is only one factor — throughput, latency, and context limits differ between providers.
Does SambaNova offer batch or cached pricing for DeepSeek V3.2?
We track 1 DeepSeek V3.2 offering from SambaNova. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.