The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.
curl https://api.aigateway.sh/v1/chat/completions \
-H "Authorization: Bearer $AIGATEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta/llama-3.2-11b-vision-instruct",
"messages": [{"role":"user","content":"hello"}],
"stream": true
}'{
"model": "meta/llama-3.2-11b-vision-instruct",
"messages": [
{ "role": "system", "content": "You are a helpful assistant." },
{ "role": "user", "content": "Hello!" }
],
"temperature": 0.7,
"top_p": 0.95,
"max_tokens": 1024,
"stream": false
// For vision: messages[].content can be an array of
// { type: "text", text: "..." } and
// { type: "image_url", image_url: { url: "https://..." } }
}{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1776947082,
"model": "meta/llama-3.2-11b-vision-instruct",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 24,
"completion_tokens": 12,
"total_tokens": 36
}
}"stream": true// 1. Role announcement (first chunk):
data: {"choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
// 2. Content chunks (final answer):
data: {"choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
data: {"choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}
// Finish chunk:
data: {"choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
// Terminator:
data: [DONE]# pip install aigateway-py openai
# aigateway-py adds sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK covers chat — drop-in per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
stream = client.chat.completions.create(
model="meta/llama-3.2-11b-vision-instruct",
messages=[{"role": "user", "content": "Hello!"}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="", flush=True)