Llama
Llama-4-Scout-17B-16E-Instruct-FP8
Canonical ID:
llama/llama-4-scout-17b-16e-instruct-fp8
Open multimodal Llama model for long-context analysis and efficient agents
Overview
- Provider
-
Llama
- Family
- 4-scout-17b-16e-instruct-fp8
- Release date
- 2025-04-05
- Last updated
- 2025-04-05
- Input modalities
- text, image
- Output modalities
- text
Pricing and Limits
Token pricing
- Input
- $0/1M
- Output
- $0/1M
- Cached input
- N/A
Context and output
- Context window
- 128,000
- Max output tokens
- 4,096
- Qualified ID
- llama/llama-4-scout-17b-16e-instruct-fp8
Model Summary
Llama-4-Scout-17B-16E-Instruct-FP8 is a model listing in the Llama provider catalog. It is categorized under the 4-scout-17b-16e-instruct-fp8 family.
The model supports text, image modalities across input/output paths. Reported context capacity is 128,000. Pricing is listed at $0/1M input and $0/1M output.
More From Llama
Related models from the same provider catalog.
Llama
Cerebras-Llama-4-Maverick-17B-128E-Instruct
llama/cerebras-llama-4-maverick-17b-128e-instruct
Llama
Cerebras-Llama-4-Scout-17B-16E-Instruct
llama/cerebras-llama-4-scout-17b-16e-instruct
Llama
Groq-Llama-4-Maverick-17B-128E-Instruct
llama/groq-llama-4-maverick-17b-128e-instruct
Llama
Llama-3.3-70B-Instruct
llama/llama-3.3-70b-instruct
Llama
Llama-3.3-8B-Instruct
llama/llama-3.3-8b-instruct
Llama
Llama-4-Maverick-17B-128E-Instruct-FP8
llama/llama-4-maverick-17b-128e-instruct-fp8