Llama 3.2 11b Vision Instruct
by Nvidia · listed Sep 2024TVW
Open Llama multimodal model for image understanding and text reasoning
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
meta/llama-3.2-11b-vision-instruct- Context window
- 128K tokens
- Max output
- 4K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Dec 2023
- Released
- 2024-09-18
- Last updated
- 2024-09-18
- Provider docs
- docs.api.nvidia.com/nim/
Back of the envelope
≈
Also listed at
- GitHub Modelsfree in · free out
- Cloudflare Workers AI$0.0485 in · $0.676 out
- Cloudflare AI Gateway$0.049 in · $0.68 out
- Kilo Gateway$0.049 in · $0.049 out
- Inference$0.055 in · $0.055 out
- OpenRouter$0.345 in · $0.345 out
- Azure$0.37 in · $0.37 out
- Azure Cognitive Services$0.37 in · $0.37 out