Intelligence
6 scoreMeta · Flagships Analysis
Llama 3.2 90B (Vision)
Intelligence, Performance & Price Analysis
Canonical slug: llama-3-2-instruct-90b-vision · Canonical model registry at build time
Speed
58.9 output tokens/secLatency
1.20s TTFTInput Price
$1.38 / 1M tokensOutput Price
$1.38 / 1M tokensExecutive Assessment
Routing Verdict & Tradeoffs
Ethen Routing Verdict
Budget-friendly / task-specific model
Llama 3.2 Instruct 90B (Vision) scores 6 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 7). Llama 3.2 Instruct 90B (Vision) generates output at 58.9 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight non-reasoning models of similar size (median: 81.5 t/s). Llama 3.2 Instruct 90B (Vision) costs $1.38 per 1M input tokens (at the higher end, median: $0.53) and $1.38 per 1M output tokens (somewhat higher than average, median: $1.05), based on the median across providers serving the model.
Best for high-volume, simple, or domain-specific tasks where cost or speed matters more than deep reasoning.
Task Fit Assessment
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | suboptimal | Intelligence score 6 is better suited for straightforward tasks than multi-step reasoning. |
| High-volume chat & customer-facing | optimal | Output speed 58.9 tokens/sec is adequate for chat. |
| Latency-sensitive applications | optimal | TTFT 1.20s — adequate latency for most interactive use cases. |
| Cost-sensitive pipelines | optimal | Output pricing at $1.38 is reasonable for moderate volume. |
Cost Pressure Analysis
High
Pricing is premium — input $1.38, output $1.38. This model is expensive for high-volume or output-heavy workloads.
Technical Specifications
Architecture and Limits
| Specification | Value | Validation Authority |
|---|---|---|
| Model type | Open weights | inferred |
| Reasoning | No | faq |
| Input modalities | Llama 3.2 Instruct 90B (Vision) supports image input. | faq |
| Output modalities | Llama 3.2 Instruct 90B (Vision) supports text only output. | faq |
| Context window | 130k tokens | faq |
| Open weights / source | Yes, Llama 3.2 Instruct 90B (Vision) is open weights. The model weights are publicly available and can be downloaded for self-hosting. | faq |
| Parameters | Llama 3.2 Instruct 90B (Vision) has 90 billion parameters. | faq |
| License | Llama 3.2 Instruct 90B (Vision) is released under the LLAMA 3.2 COMMUNITY LICENSE AGREEMENT license. This license allows commercial use. | faq |
| Knowledge cutoff | Llama 3.2 Instruct 90B (Vision) has a knowledge cutoff of December 2023. The model's training data includes information up to this date. | faq |
| API availability | Yes, Llama 3.2 Instruct 90B (Vision) is available via API through 2 providers. | faq |
Evidence charts
Profile visualizations
Charts are the same canonical evidence cards previously published for this slug, contained inside the D18D page grammar.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Openness Index: Score
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Output Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
End-to-End Response Time
Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Latency: Time To First Answer Token
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Time per Intelligence Index Task
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Model Size: Total and Active Parameters
Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger models generally perform better but cost more to serve. Active parameter count matters for inference efficiency.
Methodology
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for Llama 3.2 90B (Vision).
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Frequently Asked Questions
Model FAQs & Technical Disclosures
Llama 3.2 Instruct 90B (Vision) was released on September 25, 2024.
Llama 3.2 Instruct 90B (Vision) was created by Meta.
Llama 3.2 Instruct 90B (Vision) scores 6 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 7).
Llama 3.2 Instruct 90B (Vision) generates output at 58.9 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight non-reasoning models of similar size (median: 81.5 t/s).
Llama 3.2 Instruct 90B (Vision) has a time to first token (TTFT) of 1.20s (based on the median across providers serving the model), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.59s).
Llama 3.2 Instruct 90B (Vision) costs $1.38 per 1M input tokens (at the higher end, median: $0.53) and $1.38 per 1M output tokens (somewhat higher than average, median: $1.05), based on the median across providers serving the model.
Llama 3.2 Instruct 90B (Vision) costs $1.38 per 1M input tokens and $1.38 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.38 per 1M tokens. Pricing may vary by provider.
No, Llama 3.2 Instruct 90B (Vision) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Llama 3.2 Instruct 90B (Vision) supports image input.
Llama 3.2 Instruct 90B (Vision) supports text only output.
Yes, Llama 3.2 Instruct 90B (Vision) supports image input and can analyze, describe, and answer questions about images.
No, Llama 3.2 Instruct 90B (Vision) is not multimodal. It only supports image input.
Llama 3.2 Instruct 90B (Vision) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Llama 3.2 Instruct 90B (Vision) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Llama 3.2 Instruct 90B (Vision) has 90 billion parameters.
Llama 3.2 Instruct 90B (Vision) is released under the LLAMA 3.2 COMMUNITY LICENSE AGREEMENT license. This license allows commercial use.
Llama 3.2 Instruct 90B (Vision) achieves a score of 6 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Llama 3.2 Instruct 90B (Vision) has a knowledge cutoff of December 2023. The model's training data includes information up to this date.
Yes, Llama 3.2 Instruct 90B (Vision) is available via API through 2 providers.
Llama 3.2 Instruct 90B (Vision) is available through 2 API providers.