Llama 3.2 11B Vision Instruct

by Meta

All Meta releases

Llama 3.2 11B Vision Instruct is Meta's mid-size multimodal model, released September 2024. With 11 billion parameters and a 131,072-token context window, it accepts images alongside text and produces text, enabling image analysis, visual question answering, and grounded reasoning over documents and graphics. The model interprets layouts, charts, diagrams, and visual content within conversational workflows, and supports tool calling so downstream applications can act on visual insights programmatically. It fits document processing workflows, accessible content description, visual search systems, and tasks requiring scene understanding. Its open-weight design permits fine-tuning for domain-specific vision tasks, and the moderate parameter count keeps multimodal inference tractable.

Key info

Input
Output
Features
Context window
131K
Max output
131K
Input price
$0.24 /1M
Output price
$0.24 /1M
Released
  • US residency available
  • Zero data retention on pay-as-you-go
  • No training by default
  • no-KYC deposit available

Available routes

Llama 3.2 11B Vision Instruct runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance β€” full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
USZero data retentionNo$0.24$0.24

Uptime and availability

Llama 3.2 11B Vision Instruct runs on a single route through the qynio gateway today, so its availability is that provider's availability.

100%route uptime, last 30 days
Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.

Data handling per route

Each route hosting Llama 3.2 11B Vision Instruct has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.

DeepInfra β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is on by default on Pay-as-you-go β€” no action required. No training on customer data. US; unknown; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
unknown

Benchmarks

Independent benchmark scores β€” composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#576 of 630 LLMs
TierEfficient
Output speed27 tok/s
First token0.56s
Intelligence Index3.0
Math Index1.7
Reasoning & knowledge
MMLU-Pro
46%
GPQA Diamond
22%
Humanity's Last Exam
6%
Long-context reasoning
16%
Coding
LiveCodeBench
11%
SciCode
11%
Agentic & tool use
Terminal-Bench Hard
1%
τ²-Bench Telecom
15%
Math & instruction following
AIME 2025
2%
IFBench
30%

Get started

Call Llama 3.2 11B Vision Instruct through the qynio gateway with one API key. Let your coding agent set it up, or call it directly β€” qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.QYN_API_KEY,
baseURL: "https://api.qyn.io/v3/compat",
});
const completion = await client.chat.completions.create({
model: "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Llama 3.2 11B Vision Instruct with…

Side-by-side on privacy, crypto rails, pricing, and benchmarks.

Other models from Meta

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation