Llama 3.3 70B Instruct

llama-3.371B

Meta's Llama 3.3 70B instruction-tuned model.

Context
131K
Max output
3K
Input price
$0.6/1M tokens
Output price
$1.2/1M tokens

Capabilities

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

Details

Model IDMeta-Llama-3.3-70B-Instruct
Familyllama-3
Licensellama-3.3
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters71B
Architecture—
Context window131K tokens
Max input—
Max output3K 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.sambanova.ai/v1/chat/completions

Pricing

Input
$0.6
Output
$1.2
Cache write
—
Cache read
—
Batch in
—
Batch out
—

API

GET/v1/models/sambanova/Meta-Llama-3.3-70B-Instruct

Llama 3.3 70B Instruct

Meta-Llama-3.3-70B-Instruct

Meta's Llama 3.3 70B instruction-tuned model.

Changes · 3 entries
Meta-Llama-3.3-70B-Instructupdate20c73acJul 17, 2026, 02:34 AM
max_output_tokens131072→3072
Meta-Llama-3.3-70B-Instructupdate53ef452Jul 9, 2026, 02:32 AM
max_output_tokens3072→131072
Meta-Llama-3.3-70B-Instructcreate3e56cf1Apr 26, 2026, 07:23 PM