Model
Model
meta-llama
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...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| DeepInfradeepinfra/fp8/flex | fp8 | $0.08 | $0.24 |
| DeepInfradeepinfra/fp8 | fp8 | $0.10 | $0.30 |
| DeepInfradeepinfra/fp8/priority | fp8 | $0.15 | $0.45 |
| Googlegoogle-vertex/us-east5 | — | $0.25 | $0.70 |
Prices are what the Provider charges, synced 2026-10-21. Amber adds its platform fee to each Trial’s total; see pricing.
Amber has no curated Model Configuration for this Model yet. Create a custom one in your Workspace to evaluate it.