Llama 3.3 70B Instruct pricing: cost per token, per answer and context window

In brief

Llama 3.3 70B Instruct pricing is $0.1 per million input tokens and $0.32 per million output tokens. One standard answer, meaning 1,000 tokens in and 500 out, costs $0.0003. The context window is 131K tokens, below the catalogue median. Inside Whizi it costs 1 credit per message and needs the Pro plan and above.

The short answer

Llama 3.3 70B Instruct pricing is $0.1 per million input tokens and $0.32 per million output tokens, with a 131K token context window. It is a Meta model, and one standard answer, meaning 1,000 tokens in and 500 tokens out, costs $0.0003. Inside Whizi it costs 1 credit per message and needs the Pro plan or above.

That makes it one of the cheaper models in the catalogue: 126 of the 139 priced models cost more per answer, and 12 cost less.

What Llama 3.3 70B Instruct costs

List rates are what the provider charges per token. The cost of one standard answer is the more useful number, because it prices the same unit of work across every model regardless of how each one is billed.

Input, per million tokens$0.1
Output, per million tokens$0.32
One standard answer$0.0003
One thousand answers$0.2600
Context window131K tokens
Credits per message in Whizi1
Minimum Whizi planPro
Rank by cost, of 143 priced models14

Prices are the published Meta rates as carried by OpenRouter, last refreshed 2026-08-20. The full dataset covering all 167 models from 43 providers is the AI model cost index, which is free to reuse with attribution.

What it costs inside Whizi

Whizi meters messages in credits rather than tokens, and Llama 3.3 70B Instruct is charged at 1 credit per message. The cost does not change with the length of your message or the length of the answer, so a one line question and a long document analysis cost the same.

PlanPrice per monthMonthly creditsMessages on this model
Pro$29.99, or $19.99 billed yearly2,5002,500
Powerhouse$49.99, or $34.99 billed yearly10,00010,000

Llama 3.3 70B Instruct is included from the Pro plan up. Pro is a curated tier rather than everything cheap: one or two current flagships per model family, each fast tier, and the high volume workhorses. See plans and limits.

How it compares on price

Against the cheapest model in the index, Ling-3.0-flash at $0.000053 per answer, Llama 3.3 70B Instruct costs 4.9 times more. Against the median, Mistral Large 4 at $0.0017, it costs 6.6 times less.

Its nearest neighbours from Meta:

ModelOne answerContextCredits
Llama 3.3 70B Instruct (this page)$0.0003131K1
Muse Ember$0.00031M1
Llama 4 Maverick$0.00061M1
Muse Glimmer 30B$0.0011131K2

It is the cheapest Meta model in the priced index, so within this provider there is nothing to route down to.

The context window in practice

Llama 3.3 70B Instruct accepts 131K tokens of context, which is roughly 200 pages of text. That is below the median for the priced catalogue.

Advertised context and usable context are not the same thing. Recall tends to degrade before the stated limit is reached, particularly for material in the middle of a long input, so the practical test is to upload a long document and ask about something buried halfway through rather than trusting the number.

The number matters most when you are working from your own files. If a document is too long for the model you picked, switching to a larger-context model in the same conversation carries the thread across, so you are not starting over. See switching models mid-conversation.

Workflow checklist
  • Input $0.1 and output $0.32 per million tokens
  • $0.0003 for one standard answer, $0.2600 for a thousand
  • 131K token context window
  • 1 credit per message inside Whizi
  • Requires the Pro plan or above
  • Ranks 14 of 143 priced models by cost per answer
Common questions

Frequently asked questions

What is Llama 3.3 70B Instruct pricing per million tokens?

$0.1 per million input tokens and $0.32 per million output tokens at list rates, which works out to $0.0003 for one standard answer of 1,000 tokens in and 500 out, or $0.2600 for a thousand of them. Inside Whizi it is 1 credit per message on a monthly allowance, rather than metered per token.

Which Whizi plan includes Llama 3.3 70B Instruct?

Pro and above, which is $29.99 per month or $19.99 billed yearly. At 1 credits per message, a Pro allowance of 2,500 credits covers 2,500 messages on this model if you spend the whole allowance here, and most people mix in a 1 credit model for routine work so it goes further.

What is the Llama 3.3 70B Instruct context window?

131K tokens, which is roughly 200 pages of text and sits below the median for the priced catalogue. Treat that as the ceiling rather than the working figure: recall usually degrades before the stated limit, especially for content in the middle of a long input.

Is Llama 3.3 70B Instruct expensive compared to other models?

It ranks 14 of 143 priced models by cost per answer, so 129 cost more and 13 cost less. The spread across the whole catalogue is about 2000 times from cheapest to priciest, which is far wider than most people assume, so "expensive" only means anything relative to the specific alternative you would otherwise use.