BroadRouter

SambaNova Cloud API pricing

Updated

SambaNova Cloud lists standard prices for 5 models. The cheapest is OpenAI GPT OSS 120B at USD 0.22 input and USD 0.59 output per 1M tokens; the dearest is GLM 5.3 at USD 2.80 / USD 8.80. It publishes cached-input prices for 2 of them, and lists no per-model batch, flex or priority prices on the pages we read.

SambaNova Cloud hosts models it does not train. By maker: Google 1, Meta 1, MiniMax 1, OpenAI 1, Z.ai 1. 5 prices, each read from SambaNova Cloud's own pricing page, checked 2026-11-14. BroadRouter is BroadNet's own site and does not sell SambaNova Cloud's services. Automated re-check 2026-11-16: 5 of 5 prices still matched the provider's page.

Models with a standard price
5
Median input / output
USD 0.38 / USD 1.20
Cached-input prices
2 of 5
Cheapest host for
0 of 5 shared models

Which models is SambaNova Cloud the cheapest provider for?

None. Every one of the 5 models that SambaNova Cloud shares with other providers is cheaper elsewhere at the standard tier. The closest is MiniMax M3.1 Flash, where SambaNova Cloud ranks 9 of 9. It is the dearest provider for 2.

The 5 models SambaNova Cloud sells that the most other providers also sell, with SambaNova Cloud's rank among them on the 3:1 blend.

SambaNova Cloud on the most widely hosted models
ModelSambaNova CloudRankCheapest
GLM 5.3USD 2.80 / USD 8.8024 of 24DeepInfra USD 0.5625 / USD 2.50
OpenAI GPT OSS 120BUSD 0.22 / USD 0.5919 of 21CoreWeave Forge USD 0.03 / USD 0.17
Llama 3.3 70BUSD 0.60 / USD 1.2011 of 14DeepInfra USD 0.10 / USD 0.32
Gemma 4 31BUSD 0.38 / USD 1.1511 of 12CoreWeave Forge USD 0.10 / USD 0.34
MiniMax M3.1 FlashUSD 0.30 / USD 1.209 of 9MiniMax USD 0.15 / USD 0.60

Which model makers does SambaNova Cloud sell?

SambaNova Cloud prices models from 5 makers. Google leads with 1 model. Standard prices, USD per 1M input / output tokens.

SambaNova Cloud models by maker
MakerModelsCheapest modelMedian input / output
Google1Gemma 4 31B USD 0.38 / USD 1.15—
Meta1Llama 3.3 70B USD 0.60 / USD 1.20—
MiniMax1MiniMax M3.1 Flash USD 0.30 / USD 1.20—
OpenAI1OpenAI GPT OSS 120B USD 0.22 / USD 0.59—
Z.ai1GLM 5.3 USD 2.80 / USD 8.80—

SambaNova Cloud price list

USD per 1M tokens: 5 prices for 5 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means SambaNova Cloud is cheaper. Of 2 hosted model prices with a maker price to compare, 0 are below the maker's and 2 above.

SambaNova Cloud API prices by model
ModelTierInputCachedOutputContextvs makerSource
Gemma 4 31BstandardUSD 0.38—USD 1.15not stated—source
GLM 5.3standardUSD 2.80USD 0.14USD 8.80not stated+100%source
Llama 3.3 70BstandardUSD 0.60—USD 1.20not stated—source
MiniMax M3.1 FlashstandardUSD 0.30USD 0.03USD 1.20not stated+100%source
OpenAI GPT OSS 120BstandardUSD 0.22—USD 0.59not stated—source
  • Cached "—" means SambaNova Cloud's page shows no cache price for that row; budget cached tokens at the input price.
  • Context "not stated": SambaNova Cloud's pricing page does not give context windows.

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What service tiers does SambaNova Cloud publish?

Standard prices only: SambaNova Cloud publishes no per-model batch, flex, priority or fast price on the pages we read.

Cached input: 2 of 5 standard prices include a cache-read price, a median 8% of the input price. What cached input means.

What we recorded about SambaNova Cloud's pricing page: Public pricing table at cloud.sambanova.ai/plans/pricing (columns: cached input, input, output per 1M tokens). Only five models are listed; context windows not stated there.

Is SambaNova Cloud cheaper than the model makers' own APIs?

Mostly no. Of 2 standard prices for models whose maker sells its own API, 0 are below the maker's price, 2 above and 0 the same, on the 3:1 blend. The median difference is 100% above the maker. The biggest markup is MiniMax M3.1 Flash, 100% above MiniMax.

BroadNet Inference and SambaNova Cloud

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 1 model that SambaNova Cloud prices: GLM 5.3 at USD 0.78 / USD 3.46 against SambaNova Cloud's USD 2.80 / USD 8.80 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.

More on SambaNova Cloud

Questions

How much does the SambaNova Cloud API cost per token?

SambaNova Cloud's standard prices run from USD 0.22 input and USD 0.59 output per 1M tokens (OpenAI GPT OSS 120B) to USD 2.80 / USD 8.80 (GLM 5.3). The median across 5 standard prices is USD 0.38 input and USD 1.20 output per 1M, which is USD 0.00000038 per input token. Input, cached input and output are billed separately.

What is the cheapest model on SambaNova Cloud?

OpenAI GPT OSS 120B, at USD 0.22 input and USD 0.59 output per 1M tokens (USD 0.3125 on a 3:1 input-to-output blend). The cheapest from other makers: Gemma 4 31B (Google) at USD 0.38 / USD 1.15; Llama 3.3 70B (Meta) at USD 0.60 / USD 1.20; MiniMax M3.1 Flash (MiniMax) at USD 0.30 / USD 1.20.

Is SambaNova Cloud cheaper than other providers?

It depends on the model. Of 5 models that other providers also price, SambaNova Cloud is the cheapest standard price for none; another provider is cheaper for 5; and it is the dearest for 2. Its median rank is 11 of a median 14 providers, on a 3:1 input-to-output blend.

Does SambaNova Cloud have batch, cached or priority pricing?

Cached input: yes, for 2 of 5 standard prices, at a median 8% of the input price. No batch, flex or priority prices are listed per model on the pages we read.

How much does a chatbot cost per month on SambaNova Cloud?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 30.42 on OpenAI GPT OSS 120B, USD 54.90 on Gemma 4 31B (the middle of SambaNova Cloud's list) and USD 266.76 on GLM 5.3. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity