Llama 3.1 8B Instruct fp8 model ID, context window & pricing
llama
Quick facts
Model ID @cf/meta/llama-3.1-8b-instruct-fp8
Source Cloudflare Workers AI
Context Window 32000
Pricing $0.15 input / $0.29 output per 1M tokens
Capabilities temperature control, open weights
Model overview
Llama 3.1 8B Instruct fp8 is an AI model from Cloudflare Workers AI with 32000 token context window and text input support.
Published pricing is $0.15 input and $0.29 output per 1M tokens.
- Workloads that use text inputs with text outputs.
Model ID @cf/meta/llama-3.1-8b-instruct-fp8
Provider Cloudflare Workers AI
Family llama
Status -
Knowledge Cutoff -
Release Date 2024-07-25
Input Modalities text
Output Modalities text
Context Window 32000
Input Limit -
Output Limit 32000
Tool Calling No
Reasoning No
Structured Output No
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.15
Output Cost / 1M tokens $0.29
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -