llama-3.3-70b-instruct

completions

On:deepinfraparasail

llama-3.3-70b-instruct

completions

Published by: metaProviders:

deepinfra parasail

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 is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. [Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md)

Provider	Input	Output
deepinfra	$0.04 / 1M tokens	$0.12 / 1M tokens
parasail	$0.15 / 1M tokens	$0.5 / 1M tokens

Released

Dec 6, 2024

Knowledge

Jun 9, 2024

Context

131072

Input

$0.04 / 1M tokens

Output

$0.12 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats	License
deepinfra	131072 tokens	$0.04 / 1M tokens	$0.12 / 1M tokens	text	text	llama_3_3_community_license_agreement
parasail	131072 tokens	$0.15 / 1M tokens	$0.5 / 1M tokens	text	text	llama_3_3_community_license_agreement

Released Dec 6, 2024Knowledge Cutoff: Jun 9, 2024

Access llama-3.3-70b-instruct through LangDB AI Gateway

Recommended

Integrate with meta's llama-3.3-70b-instruct and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Available from 2 providers

Provider:

Benchmark Results for llama-3.3-70b-instruct

Category Performance Scores:

Academia: Score 39.03 (Top 55% - Rank #190)
Finance: Score 17.80 (Top 82% - Rank #283)
Marketing: Score 41.45 (Top 48% - Rank #166)
Maths: Score 7.70 (Top 85% - Rank #294)
Programming: Score 27.40 (Top 54% - Rank #187)
Science: Score 52.78 (Top 61% - Rank #211)
Writing: Score 40.97 (Top 51% - Rank #176)

Overall Performance: 32.44722222222222 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	30.00	Top 39%	Mathematics
AA Coding Index	27.40	Top 54%	Programming
AAII	27.90	Top 49%	General
AA Math Index	7.70	Top 85%	Mathematics
GPQA	50.15	Top 58%	STEM (Physics, Chemistry, Biology)
HLE	4.00	Top 77%	General Knowledge
HumanEval	88.40	Top 31%	Programming
LiveCodeBench	28.80	Top 53%	Programming
MATH-500	77.30	Top 53%	Mathematics
MMLU	86.00	Top 43%	General Knowledge
MMLU-Pro	70.10	Top 58%	General Knowledge
SciCode	26.00	Top 54%	Scientific

MMLU Score: 86.00 - Massive Multitask Language Understanding benchmark

HumanEval Score: 88.40 - Coding capability benchmark

GPQA Score: 50.15 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepinfra

Model Type: completions

Context Size: 131072 tokens

Comparing against 345 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

30.0

Mathematics

AA Coding Index

27.4

Programming

AAII

27.9

General

AA Math Index

7.7

Mathematics

GPQA

50.2

STEM (Physics, Chemistry, Biology)

HLE

4.0

General Knowledge

HumanEval

88.4

Programming

LiveCodeBench

28.8

Programming

MATH-500

77.3

Mathematics

MMLU

86.0

General Knowledge

MMLU-Pro

70.1

General Knowledge

SciCode

26.0

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	HumanEval	LiveCodeBench	MATH-500	MMLU	MMLU-Pro	SciCode
Score	30.0	27.4	27.9	7.7	50.2	4.0	88.4	28.8	77.3	86.0	70.1	26.0

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for llama-3.3-70b-instruct

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="llama-3.3-70b-instruct",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "llama-3.3-70b-instruct",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b-instruct",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: llama-3.3-70b-instruct

Provider: deepinfra

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from deepinfra

llama-3.3-70b-instruct

llama-3.3-70b-instruct

Access llama-3.3-70b-instruct through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B

llama-3.3-70b-instruct by deepinfra - AI Model Details, Pricing, and Performance Metrics

llama-3.3-70b-instruct

llama-3.3-70b-instruct

Access llama-3.3-70b-instruct through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B