Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All Groq models
Groq
GroqMultimodal

Llama 3.2 11B Vision (Groq)

Fast Vision

Smaller Llama 3.2 vision model — fits on a single GPU while keeping multimodal capability.

Llama 3.2 11B Vision (Groq) is a multimodal AI model from Groq. It costs $0.180 per million input tokens and $0.180 per million output tokens (blended $0.180/M), with a 128K-token context window.

Profile inherited from upstream Llama 3.2 11B Vision ↗ — this is a hosted variant of the same open-weights model.

Released Sep 2024Modalities text, visionOfficial model page ↗Provider pricing ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.180/M
per million input tokens
OUTPUT
$0.180/M
per million output tokens
BLENDED 70/30
$0.180/M
default reference rate · how it's calculated →
CONTEXT
128K
128,000 tokens
What it's good at
  • Single-GPU vision
  • Open weights
  • Cheap multimodal
Typical use cases
  • On-prem vision QA
  • Cheap multimodal RAG
  • Fine-tune base
Benchmarks
vs. best public score
Scores inherited from Llama 3.2 11B Vision — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU73%
Multitask academic knowledge across 57 subjects.
GPQA Diamond33%
Graduate-level science questions, "Google-proof".
MATH51%
High-school competition math problems.
HumanEval64%
Python function synthesis from docstrings.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
More from Groq
See all 11 →
Llama 3.3 70B (Groq)
Ultra-Fast · 128K ctx
in $0.590/Mout $0.790/M
Llama 3.1 405B (Groq)
Fast Large · 128K ctx
in $2.990/Mout $2.990/M
Llama 3.1 70B (Groq)
Fast · 128K ctx
in $0.590/Mout $0.790/M
Llama 3.1 8B (Groq)
Fast Nano · 128K ctx
in $0.050/Mout $0.080/M
Llama 3.2 3B (Groq)
Fast Micro · 128K ctx
in $0.060/Mout $0.060/M
Mixtral 8x7B (Groq)
Fast MoE · 32K ctx
in $0.240/Mout $0.240/M
Frequently asked questions

How much does Llama 3.2 11B Vision (Groq) cost?

Llama 3.2 11B Vision (Groq) costs $0.180 per million input tokens and $0.180 per million output tokens, for a blended reference rate of $0.180 per million tokens.

What is Llama 3.2 11B Vision (Groq)'s context window?

Llama 3.2 11B Vision (Groq) supports up to 128K tokens of context (128,000 tokens).

What is Llama 3.2 11B Vision (Groq) best for?

Llama 3.2 11B Vision (Groq) is well suited to Single-GPU vision, Open weights and Cheap multimodal.

Who makes Llama 3.2 11B Vision (Groq)?

Llama 3.2 11B Vision (Groq) is developed and served by Groq. It was released in Sep 2024.