Llama 3.3 70B Instruct

Meta· released 6 Dec 2024

meta-llama/llama-3.3-70b-instruct

Input / 1M tokens: $0.1
Output / 1M tokens: $0.32

Context window131K tokens

Longest answer: 16K tokens

reads textopen weightstool calling

About

Llama 3.3 70B Instruct is Meta’s 70B multilingual large language model, pretrained and instruction tuned for text input and text output. It supports tools and has open weights, with Hugging Face ID `meta-llama/Llama-3.3-70B-Instruct`. The context window is 131,072 tokens and the maximum output is 16,384 tokens. Its model ID is `meta-llama/llama-3.3-70b-instruct`. The model was released on 2024-12-06. Input costs $0.1 per 1M tokens and output costs $0.32 per 1M tokens. For teams choosing a text model, the listed details include its multilingual scope, instruction tuning, tool support, open-weights status and token limits. It is text-only, with no image input listed.

Who it is for

A fit for teams building multilingual, text-based applications that need instruction tuning or tool support. Builders considering open weights can also assess its listed model ID and token limits.

What is good

Multilingual text model
Open weights
Tool support
131,072-token context window

What to know first

Input costs $0.1 per 1M tokens
Output costs $0.32 per 1M tokens
Text input and output only

Verdict

Llama 3.3 70B Instruct offers text-based multilingual generation, tool support and open weights. Its 16,384-token maximum output and listed per-token prices are relevant constraints.

Details

Lab: Metaopenrouter.ai · 3 Oct 2026
Context: 131Kopenrouter.ai · 3 Oct 2026
Input price: $0.1 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $0.32 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 16,384 tokensopenrouter.ai · 3 Oct 2026
Inputs: textopenrouter.ai · 3 Oct 2026
Open weights: Yesopenrouter.ai · 3 Oct 2026

More longest-context models

See the list

Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouter Auto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouter Grok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAI Grok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAI Pareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouter Llama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Longest-Context Models in 2026466 listed
Newest Models in 2026466 listed
Cheapest Language Models in 2026437 listed
Models with Tool Calling in 2026395 listed
Open-Weight Models in 2026178 listed
Meta Models: Pricing per 1M Tokens and Context (2026)14 listed

Sources

openrouter.ai/meta-llama/llama-3.3-70b-instruct· checked 3 Oct 2026