Tools Web

Calculators

DeepInfra Token Cost Calculator

Estimate DeepInfra serverless LLM cost from curated open/hot models (DeepSeek, Qwen, Llama, Gemma, Nemotron) and monthly input / cached / output tokens, then apply service tier Standard (1×), Priority (1.5×), or Flex (0.8×). Partner Claude/Gemini pass-through rates are omitted from the dropdown (see footnote). GPU-hour dedicated and image models out of scope. Estimates only; official DeepInfra 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 + cached + out) × tier. Standard 1× / Priority 1.5× / Flex 0.8×. Examples (base): DeepSeek-V4-Flash-0731 $0.06/$0.015/$0.18; DeepSeek-V4-Pro $1.30/$0.10/$2.60; Kimi-K2.6 $0.75/$0.15/$3.50; Qwen3-32B $0.08/$0.28. Partner Claude/Gemini omitted from dropdown. No GPU-hour / image.Official pricing: DeepInfra pricing

Fireworks Token Cost Calculator · Together AI Token Cost Calculator · Hyperbolic Token Cost Calculator · Novita Token Cost Calculator · SiliconFlow Token Cost Calculator · OpenRouter Token Cost Calculator

More in this group

How it works

How do Standard / Priority / Flex work?
Base model rates × tier multiplier: Standard 1× (default), Priority 1.5× (ahead of standard traffic), Flex 0.8× (cheaper, slower / occasional unavailability).
Are Claude and Gemini included?
Not in the curated dropdown. Partner Claude/Gemini on DeepInfra are pass-through-style partner rows — use the Claude / Gemini token pages or paste rates from deepinfra.com/pricing.
Are results invoices?
No. Estimates only; deepinfra.com/pricing prevails. Dedicated GPU $/hr and image models are out of scope.
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.