Llama 3.3 70B Instruct

Name: Llama 3.3 70B Instruct
Brand: meta
SKU: meta/llama-3.3-70b-instruct
Price: 0.72 USD
Availability: InStock

meta/llama-3.3-70b-instruct

text in · text out · 131,072 context · 16,384 max output · uptime 100.00% · TTFT 1419 ms

toolsschemaZDRno-trainShow prices also in

Effective cost per 1k requestsInput tokens 2,000Output tokens 500Cached share 50%

cost = p_in·(input − cached) + p_cache_read·cached + p_out·output + p_req; cached tokens are the prefix a sticky endpoint already holds (part2b §9.3), which is why the cheapest list price is not always the cheapest request.

Provider	Region · quant	Context / max out	Input / M	Output / M	Cache read / write	Markup	Per 1k req	Uptime 30 d	TTFT p50 / p95	Throughput	Last 24 h	Fidelity	Data	Capabilities	Status
AWS Bedrock	us · none	131,072 / 16,384	$0.720	$0.720	— / —	+10.0%	$1.800	—	—	—	no traffic	—	no-train 30 d	model default	active
DeepInfra	us · fp8	131,072 / 16,384	$0.253	$0.440	— / —	+10.0%	$0.726	—	—	—	no traffic	—	ZDR no-train	7 differ	active
OpenRouter	global · unknown	131,072 / 16,384	$0.105	$0.336	— / —	+5.0%	$0.378	100.00%	1419 / 1419 ms	4.6 tok/s	100.00% · 1419 ms · 4.6 tok/s	—	no-train 30 d	12 differ	active

Quick start

curl https://api.ai.ml/v1/chat/completions \
  -H "Authorization: Bearer $AIML_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta/llama-3.3-70b-instruct","messages":[{"role":"user","content":"Say hello"}]}'

Get a key in the console

Changelog

new_model endpoint ep_openrouter_llama-3.3-70b-instruct_global (meta-llama/llama-3.3-70b-instruct) added as active; price input 0.105 output 0.336 USD/M 10/5/2026