The @cf/meta/llama-3.3-70b-instruct-fp8-fast AI model by Cloudflare Workers AI offers developers a powerful tool with a context window of 24,000 tokens and an output limit of 24,000 tokens, enabling advanced text input and function calling capabilities. With open weights and competitive pricing at $0.29/M input and $2.25/M output tokens, this model is ideal for a wide range of AI applications requiring large-scale processing and reasoning abilities.

Key Specifications

Context Window

24K tokens

Max Output Tokens

24K tokens

Input Pricing

$0.29

per million tokens

Output Pricing

$2.25

per million tokens

Capabilities

Text Generation
Function Calling

Additional Details

Provider: Cloudflare Workers AI
Release Date: December 6, 2024
Supported Input Types: text

Compare with Similar Models

@cf/meta/llama-3.3-70b-instruct-fp8-fast vs @hf/thebloke/mistral-7b-instruct-v0.1-awq

Compare specifications and pricing

@cf/meta/llama-3.3-70b-instruct-fp8-fast vs @cf/deepgram/aura-1

Compare specifications and pricing

@cf/meta/llama-3.3-70b-instruct-fp8-fast vs Qwen-Omni Turbo

Compare specifications and pricing