Llama 3.3 70B Instruct

llama3.370B

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

Context
12K
Max output
12K
Input price
$0.14/1M tokens
Output price
$0.4/1M tokens

Capabilities

Reasoning & Interaction
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Fine-tuning

Details

Model IDmeta-llama/llama-3.3-70b-instruct
Provider Novita AI
Creator Meta Llama
Familyllama-3.3
Licensellama3.3
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters70B
Architecture—
Context window12K tokens
Max input—
Max output12K tokens
Reasoning tokens—
Knowledge cutoff
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.novita.ai/v3/openai/v1/chat/completions

Pricing

Input
$0.14
Output
$0.4
Cache write
—
Cache read
—
Batch in
—
Batch out
—

API

GET/v1/models/novita/meta-llama/llama-3.3-70b-instruct

Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

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

Changes · 4 entries
meta-llama/llama-3.3-70b-instructcreateca7a400Nov 2, 2026, 03:02 AM
meta-llama/llama-3.3-70b-instructupdate3cddff5Aug 13, 2026, 02:54 AM
context_window6000→12288
max_output_tokens120000→12288
meta-llama/llama-3.3-70b-instructupdate53ef452Jul 9, 2026, 02:32 AM
context_window131072→6000
meta-llama/llama-3.3-70b-instructcreate08f0ffeMay 11, 2026, 08:27 AM