Meta Llama
Meta: Llama 4 Scout
meta-llama/llama-4-scout
Input / M
Output / M
Context
Max Output
16K
Usage
Unranked
Quality
Unscored
Providers
4
Best Uptime 30m
100.00%
Released
Apr 5, 2025
Modalities
text, image
About
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...
Capabilities
Vision
Tools
Reasoning
Streaming
JSON Mode
Providers · 4
Per-provider pricing, uptime
| Provider | Input/M | Output/M | Context | Max Out | Quant | Uptime 30m |
|---|---|---|---|---|---|---|
| Novita Novita | meta-llama/llama-4-scout-17b-16e-instruct | $0.180 | $0.590 | 131K | 131K | bf16 | 100.00% |
| DeepInfraRecommended DeepInfra | meta-llama/llama-4-scout-17b-16e-instruct | $0.100 | $0.300 | 328K | 16K | fp8 | 100.00% |
| Groq Groq | meta-llama/llama-4-scout-17b-16e-instruct | $0.110 | $0.340 | 131K | 8K | unknown | 99.78% |
| Google Google | meta-llama/llama-4-scout-17b-16e-instruct | $0.250 | $0.700 | 1.3M | 8K | unknown | 99.73% |
Performance History
54 snapshots
Price History
0 recorded changes
No price changes recorded yet.
Activity Timeline
- No events yet.
Versus
Nearest peers by price, context, and capabilities. One click to compare.
No comparable models found.
First seen 3d ago · Last verified 8m ago