← Back to AI API
✦ NEW DEAL
Cloudflare · AI API · Model API

Cloudflare Workers AI — Llama 3.3 70B FP8 Fast

Cloudflare Workers AI offers @cf/meta/llama-3.3-70b-instruct-fp8-fast at USD $0.293 per million input tokens and $2.253 per million output tokens. The model has a 24,000-token context window and supports function calling and batch; Workers AI provides a shared 10,000-neuron daily free allocation, with usage beyond that requiring Workers Paid.

INPUT / 1M$0.29Native listed metric
OUTPUT / 1M$2.25Native listed metric
Fit & constraints

Fit & constraints

Use-case fit and limitations from the existing resource record.

AVAILABILITY

Available

Resource facts

Technical profile

Non-price resource facts only; pricing, history, and evidence stay in their own sections.

CONTEXT24,000
AI MODEL@cf/meta/llama-3.3-70b-instruct-fp8-fast
Trust layer

Verified evidence

Decision visuals remain traceable to the existing source and verification record.

Verified
EvidenceOfficial

Independent ranking · native prices · evidence-linked · commercial relationships isolated from scoring and publication.