Meta
FastLlama 3.1 8B
Open source, fast inference. Great for simple tasks.
Capabilities
Chat
Streaming
Specifications
Context Window
128,000 tokens
Max Output
4,096 tokens
Knowledge Cutoff
December 2023
Pricing
Input
$0.06 / 1M tokens
Output
$0.06 / 1M tokens
Prices shown are base OpenRouter rates. Xpay adds a 5% markup.
Chat
API
Chat
Start a conversation with Llama 3.1 8B
Type a message below to begin
