Primary use stated or inferred cautiously from official documentation.
META / Llama-4-Scout-17B-16E-Instruct
Llama 4 Scout
Multimodal model with 17B active parameters and 16 experts, designed for context up to 10 million tokens.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | Llama-4-Scout-17B-16E-Instruct |
|---|---|
| Model type | Text and reasoning · Vision and documents |
| Access model | Open weights |
| License | Llama Community License |
| Deployment | Local, private cloud, or provider |
| Release | 5 APR 2025 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image |
| Exit | Text |
| Context window | 10,000,000 tokens |
| maximum output | Not published |
| Reasoning | Not applicable or not published |
| Published tools | |
| Structured Outings | Not applicable or not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Downloadable weights |
| Verified platforms | Meta Llama · Hugging Face · Nubes asociadas |
Very long context, documents, and vision with deployment control.
The license is not Apache/MIT, and the maximum context requires substantial memory and retrieval testing.
03 / CAPABILITIES
What it can do
Orientation
Very long context, documents, and vision with deployment control.
Context
10,000,000 tokens · Not published
Tools and integration
Not published
Access
Direct download and providers
Input modalities
TextImage
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Consult the primary source: the billing unit depends on the model type and access channel.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| Evaluaciones Llama 4 Scout | Best-in-class leadership | Multimodal and long context | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Llama 4 Scout
Version added to Inferama's verified catalog.
07 / SOURCES