Llama-3.2-90B-Vision-Instruct
by Azure · family llama · listed Sep 2024TVW
Open Llama multimodal model for image understanding and text reasoning
Current rates USD per 1M tokens
Input$2.04
Output$2.04
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
llama-3.2-90b-vision-instruct- Context window
- 128K tokens
- Max output
- 8K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Dec 2023
- Released
- 2024-09-25
- Last updated
- 2024-09-25
← All Azure listings