llama-3.3-70b-versatile

meta-llama/Llama-3.3-70B-Versatile

Context

128K

Input

text

Output

text

Tool calling

Supported

About this model

Llama-3.3-70B-Instruct is Meta's flagship 70B parameter model featuring enhanced reasoning, 128K context, and enterprise-grade instruction following. Represents a significant evolution over Llama 3.1 with improved tool integration, safety alignment, and complex task handling.

Compare Text Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Groq

Available

Input tokens

$0.590 / 1M tokens

Output tokens

$0.790 / 1M tokens

Routing

OneInfer optimized

Novita

Available

Input tokens

$0.130 / 1M tokens

Output tokens

$0.390 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Input tokens	$0.590 / 1M tokens
Output tokens	$0.790 / 1M tokens

Performance

Published evaluation results associated with this model.

General Reasoning

MMLU82.7

ARC-Challenge89.4

HellaSwag87.9

Winogrande84.3

Mathematical Reasoning

GSM8K92.8

MATH53.6

Coding

HumanEval76.4

MBPP79.2

CRUXEval71.8

Long-Context

Needle-128K99.3

PG-22 Recall95.1

GovReport-QA92.8

Safety & Alignment

ToxiGen96.2

TruthfulQA73.5

Harmfulness0.4

Efficiency

Tokens/sec (8×H100)68

First Token Latency0.85

VRAM Utilization145

API example

Refer Documentation

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3.3-70B-Versatile",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'