Bedrock
99.98%Context128K
Max output8.2K
p50 latency225 ms
Throughput216.5 t/s
Input price$0.17
Output price$0.66
Zero retentionNo training
Model directory
Baseer model profileLanguage model
meta/llama-4-scout
Llama 4 Scout 17B Instruct
Llama 4 Scout is the best multimodal model in the world in its class and is more powerful than our Llama 3 models, while fitting in a single H100 GPU. Additionally, Llama 4 Scout supports an industry-leading context window of up to 10M tokens.
Input / 1M tokens$0.1
Output / 1M tokens$0.3
Maximum context131.1K
Inference providers2
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Deepinfra
100.00%Context131.1K
Max output8.2K
p50 latency576 ms
Throughput51.5 t/s
Input price$0.1
Output price$0.3
Zero retentionNo training
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Bedrock | 128K | 8.2K | 225 ms | 216.5 t/s | 99.983% | $0.17 | $0.66 | |
Deepinfra | 131.1K | 8.2K | 576 ms | 51.5 t/s | 100.000% | $0.1 | $0.3 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageTool useVisionTools
Technical profile
- Model type
- Language model
- Release date
- Apr 5, 2025
- Knowledge cutoff
- 2024-08
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
meta/llama-4-scoutModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.