Model prices / Meta / Llama-3.2-90B-Vision-Instruct
Llama-3.2-90B-Vision-InstructOpen weights
Meta · released 2024-09-25
Llama-3.2-90B-Vision-Instruct is only on record at providers that price it at 0 (as of 2026-11-12). Context window: 128K tokens, up to 8.2K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Nvidiameta/ | $0 | $0 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Large open multimodal Llama model for image reasoning, document QA, and captioning
Description from models.dev.
Specs
- Type
- Text
- Context
- 128K
- Max output
- 8.2K
- Input
- Text, Image
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- —
- Knowledge cutoff
- 2023-12
- Open weights
- Yes
- Released
- 2024-09-25
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.