Using Llama 3.2 90B Vision Instruct on Bitdeer AI
Implementation guide · Llama 3.2 · AI at Meta
Quick Start
- 1
- 2Use the Bitdeer AI SDK or REST API to call
llama-3.2-90b-vision-instruct— see the documentation for request format. - 3
Code Examples
About Bitdeer AI
Bitdeer AI Cloud offers both serverless (pay-per-use) and dedicated (reserved GPU) deployment options for LLM inference. The platform provides OpenAI-compatible API endpoints and supports fine-tuning on dedicated instances. Models are hosted on NVIDIA H100/H200/A100 GPUs with automatic scaling.
Bitdeer Technologies Group is a Singapore-based AI infrastructure and cloud computing company. The company provides AI Cloud, a serverless and dedicated inference platform for deploying and scaling LLM and generative AI models.
Pricing on Bitdeer AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.15 |
| Output tokens | $0.45 |
Capabilities
About Llama 3.2 90B Vision Instruct
Instruction-tuned 90B Llama 3.2 Vision model for higher-capability image reasoning, visual question answering, visual grounding, and captioning. NVIDIA NIM lists text plus image input, text output, and a 128K context window for the Llama 3.2 Vision collection.