whichllm — Browse and compare AI model specs and pricing

OpenRouter

Llama 3.1 8B Instruct model ID, context window & pricing

llama

Quick facts

Model ID meta-llama/llama-3.1-8b-instruct
Source OpenRouter
Context Window 16384
Pricing $0.02 input / $0.05 output per 1M tokens
Capabilities tool calling, structured output, temperature control, open weights

Model overview

Llama 3.1 8B Instruct is an AI model from OpenRouter with 16384 token context window and text input support.

Published pricing is $0.02 input and $0.05 output per 1M tokens.

  • Workloads that use text inputs with text outputs.
  • Agent and tool workflows that need function calling.
Model ID meta-llama/llama-3.1-8b-instruct
Provider OpenRouter
Family llama
Status -
Knowledge Cutoff 2023-12-31
Release Date 2024-07-23
Input Modalities text
Output Modalities text
Context Window 16384
Input Limit -
Output Limit 16384
Tool Calling Yes
Reasoning No
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.02
Output Cost / 1M tokens $0.05
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -