Llama 3.2 90B Instruct

by Meta

Llama 3.2 90B Instruct is a model from Meta, released on September 25, 2024. It has a 128K-token context window and can generate up to 128K output tokens. API pricing is $0.35 per 1M input tokens and $0.4 per 1M output tokens. It ranks #171 of 220 models by Intelligence Score with a score of 5.2.

Llama 3.2 90B is a large multimodal language model optimized for visual recognition, image reasoning, and captioning tasks. It supports a context length of 128,000 tokens and is designed for deployment on edge and mobile devices, offering state-of-the-art performance in image understanding and generative tasks.

Key specs

ProviderMeta
Release date2024-09-25
Licenseopen weights
Context window128K tokens
Max output128K tokens
Input price$0.35 / 1M tokens
Output price$0.4 / 1M tokens
Intelligence Score5.2

Quick answers

What is the context window of Llama 3.2 90B Instruct?

Llama 3.2 90B Instruct has a context window of 128K tokens, with a maximum output of 128K tokens per response.

How much does Llama 3.2 90B Instruct cost?

Llama 3.2 90B Instruct costs $0.35 per 1M input tokens and $0.4 per 1M output tokens through the API.

Is Llama 3.2 90B Instruct open source?

Yes. Llama 3.2 90B Instruct is an open model released under the open weights license.

When was Llama 3.2 90B Instruct released?

Meta released Llama 3.2 90B Instruct on September 25, 2024.

How does Llama 3.2 90B Instruct compare to Claude Opus 5.5 (Reasoning)?

Llama 3.2 90B Instruct scores 5.2 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1. Input pricing is $0.35 vs $4 per 1M tokens.

Compare on the AI leaderboard · All AI models

More models from Meta