Speka
Start free
All models
visionMeta

Llama 3.2 11B Vision

Lightweight vision-language model for fast image captioning, OCR and visual Q&A.

meta/llama-3.2-11b-vision-instruct
Retired· verified 12h agoThis model has been retired by its provider and is no longer served.

What is Llama 3.2 11B Vision?

Llama 3.2 11B Vision is Meta's vision model. Lightweight vision-language model for fast image captioning, OCR and visual Q&A. It runs on Speka's OpenAI-compatible /v1/chat/completions endpoint at $0.06 / 1M input and $0.06 / 1M output tokens, using the model ID meta/llama-3.2-11b-vision-instruct.

Test it live

Live playgroundLlama 3.2 11B Visionin-browser demo

Test Llama 3.2 11B Vision live

Send a message and watch the model respond. Multi-turn — it remembers the conversation.

How to call Llama 3.2 11B Vision via the API

Speka exposes Llama 3.2 11B Vision on an OpenAI-compatible /v1/chat/completions endpoint. Point any OpenAI SDK at https://speka.me/v1, set model to meta/llama-3.2-11b-vision-instruct, and your existing code runs unchanged.

quickstart.py
from openai import OpenAI

client = OpenAI(
    base_url="https://speka.me/v1",
    api_key="sk-speka-live-...",  # your Speka key
)

resp = client.chat.completions.create(
    model="meta/llama-3.2-11b-vision-instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
FAQ

Frequently asked questions

Llama 3.2 11B Vision is Meta's vision model. Lightweight vision-language model for fast image captioning, OCR and visual Q&A. It is available on Speka's OpenAI-compatible API using the model ID meta/llama-3.2-11b-vision-instruct.
On Speka, Llama 3.2 11B Vision is priced at $0.06 / 1M input and $0.06 / 1M output tokens. Pricing is per-token with no subscription or seat fee — usage is billed against your plan's monthly allowance, then at the same rate with no overage penalty. Rates are current as of June 2026; check the pricing page for updates.
Speka exposes Llama 3.2 11B Vision on an OpenAI-compatible /v1/chat/completions endpoint. Set base_url to https://speka.me/v1, supply your Speka key, and set model to "meta/llama-3.2-11b-vision-instruct" in any OpenAI SDK — no other code changes are required.
Llama 3.2 11B Vision supports a 128,000-token context window — roughly 96,000 words of input, suitable for long documents, multi-turn agents, and large-context tasks.
Yes. Llama 3.2 11B Vision is served through Speka's OpenAI-compatible endpoint, so any application built on the OpenAI Python or Node.js SDK, LangChain, or LlamaIndex can call it by changing only the base URL and model ID.

More vision models

Meta logo

Llama 3.2 90B Vision

Meta
vision

Large multimodal model for image understanding, document Q&A, charts and visual reasoning.

meta/llama-3.2-90b-vision-instruct
Input / 1M
$0.35
Output / 1M
$0.40
Open model
NVIDIA logo

Nemotron Nano 12B VL

NVIDIA
vision

NVIDIA's compact vision-language model — fast document, chart and screenshot understanding for automation pipelines.

nvidia/nemotron-nano-12b-v2-vl
Input / 1M
$0.10
Output / 1M
$0.15
Open model