Tools Web

Calculators

SambaNova Cloud Cost Calculator

Estimate SambaNova Cloud inference cost from model and input / cached input / output tokens. Presets match the public pricing table (as of 2026-10-30): MiniMax-M3.1-Flash $0.03/$0.30/$1.20 cached/in/out; DeepSeek-V3.1 and V3.2 $3/$4.50; gemma-4-31B-it $0.38/$1.15; gpt-oss-120b $0.22/$0.59; Meta-Llama-3.3-70B-Instruct $0.60/$1.20 per 1M tokens. Models without a published cache rate bill cached tokens at the input rate here. Estimates only; official SambaNova pricing prevails.

Math runs in your browser. Nothing is uploaded.

Input cost
—

Cached input cost
—

Output cost
—

Estimated USD cost
—

Monthly USD
—

Estimates only; official vendor pricing prevails (2026-10-30). Cost = uncached in÷1M×rate + cached÷1M×rate + out÷1M×rate. Examples: MiniMax-M3.1-Flash $0.03/$0.30/$1.20 cached/in/out; DeepSeek-V3.1/V3.2 $3/$4.50; gemma-4-31B-it $0.38/$1.15; gpt-oss-120b $0.22/$0.59; Llama-3.3-70B $0.60/$1.20. No published cache rate → cached billed at input.Official pricing: SambaNova Cloud pricing

Groq Token Cost Calculator · Fireworks Token Cost Calculator · Together AI Token Cost Calculator · DeepSeek Token Cost Calculator

How it works

How is SambaNova Cloud priced?
USD = (uncached input ÷ 1M × input) + (cached ÷ 1M × cached) + (output ÷ 1M × output). Example: MiniMax-M3.1-Flash at $0.03/$0.30/$1.20 with 1M in + 0 cached + 200k out ≈ $0.54.
What if a model has no cached rate?
The public table lists N/A for most models except MiniMax-M3.1-Flash. This calculator bills cached tokens at the input rate when no cache column is published.
Are results invoices?
No. Estimates only; cloud.sambanova.ai/plans/pricing prevails.
Is any data uploaded?
No. These calculators and QR codes run in your browser.
Can these AI prices change?
Yes. Vendors change list prices often. Edit the $/1M or plan fields, and confirm on the official pricing page before you budget.