
Llama 3.2 90B Vision
Llama 3.2 90B Vision is a language model with 90B parameters from Meta. It is currently free at 2 providers with up to 16K tokens of context. The model understands images, supports tool calling. Its weights are open, so it can also run locally.
- Developer
- Meta
- Parameters
- 90B
- Context
- 16K tokens
- Type
- Text
- License
- Open weights
Where to use Llama 3.2 90B Vision for free
Each row is a separate free endpoint with its own limits.
| Provider | Context | Limit | Card | |
|---|---|---|---|---|
Together AI nim/meta/llama-3.2-90b-vision-instruct |
16K | Fair use (depends on server load) | — | Open |
NVIDIA Build meta/llama-3.2-90b-vision-instruct |
— | Free serverless inference for development; limits and model availability may change. | No | Open |
Quick start
curl https://api.together.xyz/v1/chat/completions \
-H "Authorization: Bearer $TOGETHER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nim/meta/llama-3.2-90b-vision-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.together.xyz/v1",
api_key="YOUR_TOGETHER_API_KEY",
)
reply = client.chat.completions.create(
model="nim/meta/llama-3.2-90b-vision-instruct",
messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.together.xyz/v1",
apiKey: process.env.TOGETHER_API_KEY,
});
const reply = await client.chat.completions.create({
model: "nim/meta/llama-3.2-90b-vision-instruct",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(reply.choices[0].message.content);Example for Together AI. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.
Benchmarks
Source: Artificial Analysis · Llama 3.2 Instruct 90B (Vision)
Similar free models
FAQ
Is Llama 3.2 90B Vision free?
Yes. As of October 29, 2026, Llama 3.2 90B Vision is free at Together AI, NVIDIA Build. Each provider has its own limits — see the table above.
What is the context window of Llama 3.2 90B Vision?
The largest context among free routes is 16,384 tokens. Some providers cap it lower.
How do I call Llama 3.2 90B Vision via API?
Use any OpenAI-compatible client with base URL https://api.together.xyz/v1, model ID nim/meta/llama-3.2-90b-vision-instruct, and a Together AI key.
How good is Llama 3.2 90B Vision?
Artificial Analysis Intelligence Index: 6.4, GPQA Diamond: 43%. For comparison, the strongest free model in the catalog right now is GLM 5.3.
Is Llama 3.2 90B Vision open-weight?
Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.