Get the app

Llama 3.3 70B Instruct: price, context window and capabilities

Prices updated 8 Nov 2026

Llama 3.3 70B Instruct is a model from Meta (meta-llama/llama-3.3-70b-instruct). It supports tool use. It costs $0.590 per million input tokens and $0.790 per million output tokens, with a 131K-token context window.

$0.590input / 1M tokens
$0.790output / 1M tokens
131Kcontext window
textaccepts

What it costs in practice

Using the listed prices: a chat turn of 2,000 input and 500 output tokens costs about $0.0016, so 10,000 such turns cost about $15.75. Summarising a 100,000-token document into 2,000 tokens costs about $0.061. A long agent run that reads 1 million tokens and writes 50,000 costs about $0.629.

Llama 3.3 70B Instruct compared with its closest rivals

ModelInput / 1MOutput / 1MContextChat turn
Llama 3.3 70B Instruct
Meta
$0.590$0.790131K$0.0016
Devstral 2 2512
Mistral AI
$0.400$2.00262K$0.0018

Rivals are the models from other providers with the same tool and reasoning support whose output price is closest to Llama 3.3 70B Instruct's.

How it compares

Among the 40 models we track, Llama 3.3 70B Instruct ranks #17 by input price and #11 by output price (1 is cheapest), and #36 by context window (1 is largest). Models with the same tool and reasoning support that cost less per output token: Llama 4 Scout ($0.300). Models with a larger context window at the same or lower output price: Llama 4 Scout (1.3M), DeepSeek V4.1 Flash 1017 (1.0M), DeepSeek V4.1 Flash (1.0M), DeepSeek V4 Flash 0731 (1.0M).

More from Meta

All Meta models on one page: Meta API pricing.

Prices and limits come from OpenRouter's public model catalogue, last synced 8 Nov 2026. Provider pricing can differ from OpenRouter's and changes often; confirm on the provider's own page before you commit. See the guide to choosing a model or the full comparison.

The daily AI brief, on your phone.

Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.

Get it on Google Play