Llama 3.1 405B Pricing & Token Cost Calculator (128K context)

What Llama 3.1 405B costs in practice

Workload	Cost / call	Cost @ 1K req/day
Light · 1K in / 300 out	$0.0046	$138.49/mo
Standard · 10K in / 2K out	$0.0420	$1278.38/mo
Heavy · 100K in / 20K out	$0.4200	$12783.75/mo

Estimates assume medium reasoning effort, no batch discounts and no prompt caching. Turn on prompt caching and the input side typically drops 50–90% — run your own mix in the free calculator preloaded with Llama 3.1 405B.

How Llama 3.1 405B compares

About this page

Prices were last verified on August 20, 2026 against Meta / Llama's official pricing page. Providers reprice frequently — see our methodology for exactly how estimates are computed, and always confirm final rates with the provider before budgeting.

Llama 3.1 405B FAQ

How much does Llama 3.1 405B cost?

Llama 3.1 405B charges $3.50 per million input tokens and $3.50 per million output tokens.

What is the context window of Llama 3.1 405B?

Llama 3.1 405B supports a context window of 128,000 tokens (128K) — roughly 96,000 English words or about 192 pages of text in a single request.

Does Llama 3.1 405B support images, audio or reasoning?

Llama 3.1 405B offers text-only processing. Prices shown via Together AI — largest open-weight model.

How do I estimate my Llama 3.1 405B bill?

A typical workload of 10K input and 2K output tokens costs about $0.0420 per call with Llama 3.1 405B. At 1,000 requests per day that is roughly $1278.38 per month. Use the free AITokenCalculator to run your exact numbers.