Skip to main content
SambaNova logo

GPT-OSS-120B API pricing on SambaNova

Every SambaNova GPT-OSS-120B rate we track, compared against 18 providers serving the same model.

Input from /1M
$0.220
Output /1M
$0.590
Price rank
#16 of 18
Last updated
September 28, 2026

The cheapest GPT-OSS-120B input price we currently track is $0.030/1M on OpenRouter.

SambaNova GPT-OSS-120B rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

SambaNova GPT-OSS-120B pricing by mode
ModeInputOutput
Standard$0.220/1M$0.590/1M

About GPT-OSS-120B

Creator
OpenAI
Context
128K
Modalities
text
Knowledge cutoff
Jan 2025
Open weights
Yes
Full GPT-OSS-120B details and every provider →

GPT-OSS-120B 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 GPT-OSS-120B cost on SambaNova?

SambaNova serves GPT-OSS-120B from $0.220 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 GPT-OSS-120B?

SambaNova ranks #16 of 18 providers we track serving GPT-OSS-120B. The cheapest input price right now is on OpenRouter. Price is only one factor — throughput, latency, and context limits differ between providers.

Does SambaNova offer batch or cached pricing for GPT-OSS-120B?

We track 1 GPT-OSS-120B 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.