ModelsLlama 3.2 90B

Llama 3.2 90B

by Meta

Ultra-cheap

Maximum cost efficiency for high-volume tasks

Pricing
Input
$0.20
per 1M tokens
Output
$0.40
per 1M tokens
Cached
N/A
per 1M tokens
Note: Released Sep 2024. First multimodal open model from Meta
Context & Output
Context Window128K tokens
Max Output32K tokens
Latency
Fast
Capabilities
Multimodal
Streaming
Function Calling
Prompt Caching
Key Strengths
What makes this model stand out
First multimodal Llama
Image+text
Open weights
Try Llama 3.2 90BCompare All Models
Similar Models in Ultra-cheap Tier
Other models with similar pricing and performance characteristics
Llama 4 Scout
Meta
Input:$0.11/M
Context:10M tokens
View Details
GPT-5 Nano
OpenAI
Input:$0.05/M
Context:272K tokens
View Details
Llama 3.1 405B
Meta
Input:$0.30/M
Context:128K tokens
View Details