F24 SALES / MODELL
Meta🇺🇸
Llama 3.2 90B Vision Instruct
Meta's instruction-tuned vision-language model supports image captioning, visual questions and document understanding. It connects a separately trained vision adapter to a Llama 3.1 language model through cross-attention layers.
Kostenlose Aggregator-Routen
Diese Aggregator-Routen sind im aktuellen oder zuletzt veröffentlichten Katalog erfasst. Jede Route behält ihre exakte Modell-ID und Thinking-Informationen.
The supplied successful test at 2026-11-05T18:53:05+00:00 establishes access to this exact NVIDIA route without a top-up using the dedicated account that had never held credit or linked a payment method. Continued availability and quotas are not established.
Limits oben: NVIDIA. Die verfügbaren Zugänge stehen unten.
NVIDIA's exact route reference identifies Meta's Llama-3.2-90B-Vision-Instruct, corresponding to the creator repository meta-llama/Llama-3.2-90B-Vision-Instruct. This identifies the instruction-tuned 90B vision release rather than its base or 11B variants. No pinned serving revision is established.
NVIDIA
Info- Denken
- Von dieser API nicht angegeben
meta/llama-3.2-90b-vision-instructQuellen zum Modell
- NVIDIA exact Llama 3.2 90B Vision Instruct model card
- NVIDIA exact Llama 3.2 90B model reference
- NVIDIA exact Llama 3.2 90B inference schema and output ceiling
- Meta exact instruction-model weight files
- NVIDIA public model catalog
- Models.dev technical catalog; inaccessible during review
- Meta official Llama 3.2 Vision card: 128K context
Über LiteLLM nutzen
Importiere die aktuelle LiteLLM-kompatible YAML und nutze die oben angezeigte exakte Modell-ID. Der Katalog stammt aus denselben geprüften Scan-Daten wie der Download.
LiteLLM-YAML herunterladenQuellen & Verweise
- NVIDIA exact Llama 3.2 90B Vision Instruct model card
- NVIDIA exact Llama 3.2 90B model reference
- NVIDIA exact Llama 3.2 90B inference schema and output ceiling
- Meta exact instruction-model card
- Meta exact instruction-model weight files
- NVIDIA public model catalog
- Models.dev technical catalog; inaccessible during review
- Meta official Llama 3.2 Vision card: 128K context