Meta: Llama 4 Scout
meta-llama/llama-4-scout
- context
- 1.31M
- modalities
- text, image → text
- capabilities
- Tool use, Vision, Structured output, Long context, Low cost
Overview
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...
Providers
- DeepInfraView DeepInfra
- GoogleView Google
- NovitaView Novita
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| DeepInfradeepinfra/fp8 · fp8 | $0.10 | $0.30 |
| DeepInfradeepinfra/fp8/flex · fp8 | $0.08 | $0.24 |
| DeepInfradeepinfra/fp8/priority · fp8 | $0.15 | $0.45 |
| $0.25 | $0.70 | |
| Novita | $0.18 | $0.59 |
DeepInfra
deepinfra/fp8 · fp8
- input / 1M
- $0.10
- output / 1M
- $0.30
DeepInfra
deepinfra/fp8/flex · fp8
- input / 1M
- $0.08
- output / 1M
- $0.24
DeepInfra
deepinfra/fp8/priority · fp8
- input / 1M
- $0.15
- output / 1M
- $0.45
Google
- input / 1M
- $0.25
- output / 1M
- $0.70
Novita
- input / 1M
- $0.18
- output / 1M
- $0.59
Use this model
through Nautili
Route requests to Meta: Llama 4 Scout through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.