Workers AI: llama-3.3-70b-instruct-fp8-fast

70B
Input price
$290000/1M tokens
Output price
$2250000/1M tokens

Capabilities

Infrastructure
Streaming

Details

Model IDworkers-ai/llama-3.3-70b-instruct-fp8-fast
Provider Cloudflare AI Gateway
Creator Cloudflare Workers AI
Familyllama-3.3
License—
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters70B
Architecture—
Context window—
Max input—
Max output—
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Pricing

Input
$290000
Output
$2250000
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: llama-3.3

ModelContextMax outPricing
OpenRouter: meta-llama/llama-3.3-70b-instruct:free———
OpenRouter: meta-llama/llama-3.3-8b-instruct:free———
OpenRouter: nvidia/llama-3.3-nemotron-super-49b-v1:free———
OpenRouter: meta-llama/llama-3.3-70b-instruct——$0.1$0.32
OpenRouter: nvidia/llama-3.3-nemotron-super-49b-v1.5——$0.1$0.4
OpenRouter: nvidia/llama-3.3-nemotron-super-49b-v1——$0.13$0.4
Groq: llama-3.3-70b-specdec——$0.59$0.99
Groq: llama-3.3-70b-versatile——$0.59$0.79
Azure OpenAI: llama-3.3-70b-instruct——$0.71$0.71
Google Vertex AI: meta/llama-3.3-70b-instruct-maas——$0.72$0.72
cerebras: llama-3.3-70b——$0.85$1.2
Workers AI: llama-3.3-70b-instruct-fp8-fast——$290000$2250000

API

GET/v1/models/cloudflare-ai-gateway/workers-ai/llama-3.3-70b-instruct-fp8-fast

Workers AI: llama-3.3-70b-instruct-fp8-fast

workers-ai/llama-3.3-70b-instruct-fp8-fast
Changes · 3 entries
workers-ai/llama-3.3-70b-instruct-fp8-fastupdate1cd659eMar 24, 2026, 04:19 AM
modalitiesinput["text"]output["text"]
workers-ai/llama-3.3-70b-instruct-fp8-fastupdate2b100acMar 23, 2026, 05:30 AM
model_typechat
parameters70
workers-ai/llama-3.3-70b-instruct-fp8-fastcreate7a4f1f6Mar 22, 2026, 05:43 AM