All AI models · LLM benchmarks · Methodology

Meta

Llama 3.1 8B Instruct fp8

Open Llama instruction model for multilingual chat, reasoning, and coding

Model facts

Context window
32K tokens
Maximum output
32K tokens
Cheapest paid input
$0.152 per 1M tokens
Cheapest paid output
$0.287 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

temperature control, open weights, text.

Observed price history

  • 2026-08-24: $0.152 input / $0.287 output per 1M tokens

API providers

  • Cloudflare Workers AI — model id @cf/meta/llama-3.1-8b-instruct-fp8; $0.152 input / $0.287 output per 1M tokens; provider documentation