meta-llama
Meta: Llama 4 Scout
meta-llama/llama-4-scout
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter lists meta-llama/llama-4-scout as Meta's Llama 4 Scout 17B Instruct (16E), a mixture-of-experts model that activates part of a larger parameter pool. The catalog reports native text-and-image input, text output, tool and structured-output controls, and a very large context window. Its Design Arena measurements are weak across the listed categories, while independent model-card evidence was not available in this source pack. Treat the profile as catalog-reported and validate it on real workloads before production use.[1]
Strengths
Limitations
- All evidence comes from the OpenRouter catalog; no independent model card was supplied, so licensing, hardware needs, deployment behavior, and safety properties remain unknown.[1]
- Measured Design Arena results are weak across the catalog's listed categories, with data visualization the strongest relative area.[1]
- OpenRouter leaves the reasoning field unset and reports an August 31, 2024 knowledge cutoff; dedicated reasoning and newer knowledge are therefore unverified.[1]
Where to use it
- Multimodal assistant prototypes that need image grounding and text responses, with output quality checked on real inputs.[1]
- Long-document summarization or analysis where the advertised context may help, after testing recall and latency.[1]
- Tool-using or structured-output workflows for low-stakes tasks, with human review because measured results are weak.[1]
Sources
- [1] OpenRouter catalog · Meta: Llama 4 ScoutSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Specifications
- Model ID
- meta-llama/llama-4-scout
- Canonical ID
- meta-llama/llama-4-scout-17b-16e-instruct
- Creator
- meta-llama
- Added to OpenRouter
- 05.04.2025
- Context length
- 1,310,720
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.100 / out $0.300
- Knowledge cutoff
- 31.08.2024
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | CC — below the B band | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 8.2 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 0.5 | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 26.6% · rank 145 | 780Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 39.3% · rank 131 | 896Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 27.4% · rank 144 | 763Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 25.5% · rank 140 | 760Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 22.7% · rank 151 | 743Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfrafp8 | 327,680 | $0.080 | $0.240 | — | — | — |
| DeepInfrafp8 | 327,680 | $0.100 | $0.300 | — | — | 100% |
| DeepInfrafp8 | 327,680 | $0.150 | $0.450 | — | — | 100% |
| 1,310,720 | $0.250 | $0.700 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.