Llama 3.3 70B Instruct

Released 2024-12-06 · Knowledge up to 2023-12-31

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

You send / 1M

$0.100

tokens in

It replies / 1M

$0.320

tokens out

Memory

131K

tokens it can read at once

Typical request

$0.0003

1,000 words in, 400 out

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

Provider	You send / 1M	It replies / 1M	Uptime	Privacy policy
DeepInfra · fp8	$0.100	$0.320	100%	Read
Novita · bf16	$0.135	$0.400	98%	Read
Parasail · fp8	$0.220	$0.500	100%	Read
AkashML · fp8	$0.200	$0.520	100%	Read
CoreWeave · fp16	$0.710	$0.710	100%	Read
Google	$0.720	$0.720	n/a	Read
Google	$0.720	$0.720	n/a	Read
Groq	$0.590	$0.790	100%	Read
SambaNova	$0.450	$0.900	97%	Read
Cloudflare · fp8	$0.293	$2.25	100%	Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

Reads: text
Writes: text
Reasoning: No
Tool calling: Yes
Longest reply: 16K tokens
Intelligence score: 7.7 / 100 (Artificial Analysis)

Similar models

Appears in

Top No-Training AI Models Top No-Training Zero Data Retention AI Models Top No-Training Zero Data Retention Cheap AI Models Top No-Training Zero Data Retention Tool-Calling AI Models Top No-Training Cheap AI Models Top No-Training Cheap Tool-Calling AI Models Top No-Training Tool-Calling AI Models Top Zero Data Retention AI Models

Estimate your monthly cost with Llama 3.3 70B Instruct →