llama-3.1-70b-instruct

completions

bydeepinfra

llama-3.1-70b-instruct

completions

Published by: metaProvider:

deepinfra

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Released

Jul 23, 2024

Knowledge

Jan 25, 2024

License

llama_3_1_community_license

Context

131072

Input

$0.1 / 1M tokens

Output

$0.28 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Released Jul 23, 2024Knowledge Cutoff: Jan 25, 2024License: llama_3_1_community_license

Context: 131072 Input: $0.1 / 1M tokensOutput: $0.28 / 1M tokensCapabilities: toolsAccepts: textReturns: text

Access llama-3.1-70b-instruct through LangDB AI Gateway

Recommended

Integrate with meta's llama-3.1-70b-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

Benchmark Results for llama-3.1-70b-instruct

Category Performance Scores:

Academia: Score 32.00 (Top 66% - Rank #228)
Finance: Score 13.35 (Top 94% - Rank #325)
Marketing: Score 33.29 (Top 74% - Rank #256)
Maths: Score 4.00 (Top 94% - Rank #325)
Programming: Score 25.00 (Top 60% - Rank #207)
Science: Score 47.22 (Top 68% - Rank #235)
Writing: Score 33.58 (Top 81% - Rank #280)

Overall Performance: 26.920238095238098 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	17.30	Top 54%	Mathematics
AA Coding Index	25.00	Top 60%	Programming
AAII	22.70	Top 62%	General
AA Math Index	4.00	Top 94%	Mathematics
DROP	79.60	Top 68%	General Knowledge
GPQA	41.30	Top 72%	STEM (Physics, Chemistry, Biology)
HLE	4.60	Top 44%	General Knowledge
HumanEval	80.50	Top 77%	Programming
LiveCodeBench	23.20	Top 69%	Programming
MATH-500	64.90	Top 70%	Mathematics
MMLU	83.60	Top 57%	General Knowledge
MMLU-Pro	67.00	Top 64%	General Knowledge
SciCode	26.70	Top 51%	Scientific

MMLU Score: 83.60 - Massive Multitask Language Understanding benchmark

HumanEval Score: 80.50 - Coding capability benchmark

GPQA Score: 41.30 - 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

17.3

Mathematics

AA Coding Index

25.0

Programming

AAII

22.7

General

AA Math Index

4.0

Mathematics

DROP

79.6

General Knowledge

GPQA

41.3

STEM (Physics, Chemistry, Biology)

HLE

4.6

General Knowledge

HumanEval

80.5

Programming

LiveCodeBench

23.2

Programming

MATH-500

64.9

Mathematics

MMLU

83.6

General Knowledge

MMLU-Pro

67.0

General Knowledge

SciCode

26.7

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	DROP	GPQA	HLE	HumanEval	LiveCodeBench	MATH-500	MMLU	MMLU-Pro	SciCode
Score	17.3	25.0	22.7	4.0	79.6	41.3	4.6	80.5	23.2	64.9	83.6	67.0	26.7

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for llama-3.1-70b-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-3.1-70b-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-3.1-70b-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-3.1-70b-instruct",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: llama-3.1-70b-instruct

Provider: deepinfra

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

Create API Key

Related Models

Similar models from deepinfra

llama-3.1-70b-instruct

llama-3.1-70b-instruct

Access llama-3.1-70b-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-3.1-70b-instruct by deepinfra - AI Model Details, Pricing, and Performance Metrics

llama-3.1-70b-instruct

llama-3.1-70b-instruct

Access llama-3.1-70b-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