Cloudflare AI Gateway

Llama 3.3 70B Instruct FP8 Fast

Name: Llama 3.3 70B Instruct FP8 Fast
Brand: Cloudflare AI Gateway

Canonical ID: cloudflare_ai_gateway/workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast

More Cloudflare AI Gateway models More llama-3.3-70b-instruct-fp8-fast family models

Llama 3.3 70B Instruct FP8 Fast is listed under Cloudflare AI Gateway in LLM Directory with pricing, context limits, modalities, and capability metadata for quick comparison.

Reasoning: Unknown Tool use: Unknown

Overview

text

Provider: Cloudflare AI Gateway
Family: llama-3.3-70b-instruct-fp8-fast
Release date: 2025-04-03
Last updated: 2025-04-03
Input modalities: text
Output modalities: text

Pricing and Limits

Token pricing

Input: $0.29/1M
Output: $2.25/1M
Cached input: N/A

Context and output

Context window: 128,000
Max output tokens: 16,384
Qualified ID: cloudflare_ai_gateway/workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast

Model Summary

Llama 3.3 70B Instruct FP8 Fast is a model listing in the Cloudflare AI Gateway provider catalog. It is categorized under the llama-3.3-70b-instruct-fp8-fast family.

The model supports text modalities across input/output paths. Reported context capacity is 128,000. Pricing is listed at $0.29/1M input and $2.25/1M output.

Same Family: llama-3.3-70b-instruct-fp8-fast

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Llama 3.3 70B Instruct FP8 Fast cloudflare_workers_ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast	Cloudflare Workers AI	128,000	$0.29/1M	$2.25/1M

Llama 3.3 70B Instruct FP8 Fast

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Cloudflare AI Gateway

BART Large CNN

BGE Base EN v1.5

BGE Large EN v1.5

BGE M3

BGE Reranker Base

BGE Small EN v1.5

Claude Haiku 3

Claude Haiku 3.5 (latest)

Same Family: llama-3.3-70b-instruct-fp8-fast