deepseek-r1-distill-llama-70b

completions

byopenrouter

deepseek-r1-distill-llama-70b

completions

Published by: deepseekProvider:

openrouter

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including: - AIME 2024 pass@1: 70.0 - MATH-500 pass@1: 94.5 - CodeForces Rating: 1633 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Released

Jan 20, 2025

Knowledge

Jul 24, 2024

License

MIT

Context

131072

Input

$0.11 / 1M tokens

Output

$0.38 / 1M tokens

Accepts: text

Returns: text

Released Jan 20, 2025Knowledge Cutoff: Jul 24, 2024License: MIT

Context: 131072 Input: $0.11 / 1M tokensOutput: $0.38 / 1M tokensAccepts: textReturns: text

Access deepseek-r1-distill-llama-70b through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-r1-distill-llama-70b 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 deepseek-r1-distill-llama-70b

Category Performance Scores:

Academia: Score 48.00 (Top 35% - Rank #114)
Finance: Score 55.50 (Top 24% - Rank #78)
Marketing: Score 22.57 (Top 61% - Rank #198)
Maths: Score 80.20 (Top 20% - Rank #65)
Programming: Score 28.90 (Top 51% - Rank #166)
Science: Score 65.20 (Top 33% - Rank #107)
Writing: Score 21.21 (Top 54% - Rank #175)

Overall Performance: 45.94 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	67.00	Top 18%	Mathematics
AA Coding Index	28.90	Top 51%	Programming
AAII	30.80	Top 41%	General
AA Math Index	80.20	Top 20%	Mathematics
GPQA	65.20	Top 33%	STEM (Physics, Chemistry, Biology)
HLE	6.10	Top 25%	General Knowledge
LiveCodeBench	26.60	Top 62%	Programming
MATH-500	93.50	Top 23%	Mathematics
MMLU-Pro	79.50	Top 25%	General Knowledge
SciCode	31.20	Top 40%	Scientific

GPQA Score: 65.20 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openrouter

Model Type: completions

Context Size: 131072 tokens

Comparing against 324 models in the database

Performance Analytics for deepseek-r1-distill-llama-70b

Usage Statistics (Last 2 Days):

Total Requests: 21 API calls
Average TPS: 361.57 tokens per second
Average Response Time: 21986.20ms
Average Time to First Token: 14141.40ms
Total Cost: $0.03
Average Request Cost: $0.0014

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/6/2025	10	599.86	19699.40ms	3225.30ms	$0.02
9/10/2025	11	184.24	24065.10ms	24065.10ms	$0.01

Performance Summary:

Model: deepseek-r1-distill-llama-70b by openrouter

Monitoring Period: 9/4/2025 to 9/11/2025

Average Daily Requests: 11

Peak Daily Requests: 11

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

361.57 tokens/s

Category Scores

maths#19

Benchmark Tests

View Other Benchmarks

AIME

67.0

Mathematics

AA Coding Index

28.9

Programming

AAII

30.8

General

AA Math Index

80.2

Mathematics

GPQA

65.2

STEM (Physics, Chemistry, Biology)

HLE

6.1

General Knowledge

LiveCodeBench

26.6

Programming

MATH-500

93.5

Mathematics

MMLU-Pro

79.5

General Knowledge

SciCode

31.2

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	67.0	28.9	30.8	80.2	65.2	6.1	26.6	93.5	79.5	31.2

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for deepseek-r1-distill-llama-70b

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="deepseek-r1-distill-llama-70b",
    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: "deepseek-r1-distill-llama-70b",
    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": "deepseek-r1-distill-llama-70b",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: deepseek-r1-distill-llama-70b

Provider: openrouter

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

Create API Key

Related Models

Similar models from openrouter

deepseek-r1-distill-llama-70b

deepseek-r1-distill-llama-70b

Access deepseek-r1-distill-llama-70b through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

codestral-2501

codestral-2508

deepseek-r1-distill-llama-70b by openrouter - AI Model Details, Pricing, and Performance Metrics

deepseek-r1-distill-llama-70b

deepseek-r1-distill-llama-70b

Access deepseek-r1-distill-llama-70b through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

codestral-2501

codestral-2508