Tools Web

Calculators

SiliconFlow Token Cost Calculator

Estimate SiliconFlow serverless LLM cost from ~15 curated presets (DeepSeek / GLM / Kimi / Qwen / MiniMax / gpt-oss / gemma). Enter monthly input, cached input, and output tokens. When a model has no published cached rate, cached tokens are billed at the input rate. Image, video, and audio models are out of scope. Estimates only; official SiliconFlow 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. Curated ~15 presets (DeepSeek/GLM/Kimi/Qwen/MiniMax/gpt-oss/gemma). No published cache → cached billed at input. No image/video/audio.Official pricing: SiliconFlow pricing

DeepInfra Token Cost Calculator · Novita Token Cost Calculator · Hyperbolic Token Cost Calculator · OpenRouter Token Cost Calculator · Together AI Token Cost Calculator · Kimi Token Cost Calculator

More in this group

How it works

Why is cached sometimes billed at input?
Some SiliconFlow rows omit a Cached Input column. This calculator then bills cached tokens at the input rate and notes it in the model list. Confirm on siliconflow.com/pricing.
Image / video / audio?
Out of scope for v1 — unit mix ($/image, $/video, audio) differs from $/1M tokens. Text LLM presets only.
Are results invoices?
No. Estimates only; siliconflow.com/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.