deepseek-r1-distill-llama-8b

completions

byopenrouter

deepseek-r1-distill-llama-8b

completions

Published by: deepseekProvider:

openrouter

DeepSeek R1 Distill Llama 8B is a distilled large language model based on [Llama-3.1-8B-Instruct](/meta-llama/llama-3.1-8b-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: 50.4 - MATH-500 pass@1: 89.1 - CodeForces Rating: 1205 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. Hugging Face: - [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) - [DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) |

Released

Jan 20, 2025

Knowledge

Jul 24, 2024

License

MIT

Context

32K

Input

$0.04 / 1M tokens

Output

$0.04 / 1M tokens

Accepts: text

Returns: text

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

Context: 32K Input: $0.04 / 1M tokensOutput: $0.04 / 1M tokensAccepts: textReturns: text

Access deepseek-r1-distill-llama-8b through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-r1-distill-llama-8b 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-8b

Category Performance Scores:

Academia: Score 34.25 (Top 65% - Rank #211)
Finance: Score 39.40 (Top 50% - Rank #162)
Marketing: Score 14.40 (Top 80% - Rank #260)
Maths: Score 59.30 (Top 40% - Rank #130)
Programming: Score 17.60 (Top 76% - Rank #247)
Science: Score 49.00 (Top 64% - Rank #208)
Writing: Score 15.20 (Top 76% - Rank #247)

Overall Performance: 32.73571428571429 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	33.30	Top 34%	Mathematics
AA Coding Index	17.60	Top 76%	Programming
AAII	19.50	Top 71%	General
AA Math Index	59.30	Top 40%	Mathematics
GPQA	49.00	Top 64%	STEM (Physics, Chemistry, Biology)
HLE	4.20	Top 75%	General Knowledge
LiveCodeBench	23.30	Top 68%	Programming
MATH-500	85.30	Top 50%	Mathematics
MMLU-Pro	54.30	Top 78%	General Knowledge
SciCode	11.90	Top 84%	Scientific

GPQA Score: 49.00 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openrouter

Model Type: completions

Context Size: 32000 tokens

Comparing against 324 models in the database

Performance Analytics for deepseek-r1-distill-llama-8b

Usage Statistics (Last 4 Days):

Total Requests: 9 API calls
Average TPS: 208.31 tokens per second
Average Response Time: 21167.50ms
Average Time to First Token: 3457.90ms
Total Cost: $0.00
Average Request Cost: $0.0002

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/4/2025	1	451.17	20588.60ms	1676.90ms	$0.00
9/5/2025	1	199.91	25641.50ms	1119.00ms	$0.00
9/6/2025	2	193.45	24763.90ms	1297.70ms	$0.00
9/10/2025	5	165.58	18949.90ms	5146.00ms	$0.00

Performance Summary:

Model: deepseek-r1-distill-llama-8b by openrouter

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

Average Daily Requests: 2

Peak Daily Requests: 5

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

208.31 tokens/s

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

33.3

Mathematics

AA Coding Index

17.6

Programming

AAII

19.5

General

AA Math Index

59.3

Mathematics

GPQA

49.0

STEM (Physics, Chemistry, Biology)

HLE

4.2

General Knowledge

LiveCodeBench

23.3

Programming

MATH-500

85.3

Mathematics

MMLU-Pro

54.3

General Knowledge

SciCode

11.9

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	33.3	17.6	19.5	59.3	49.0	4.2	23.3	85.3	54.3	11.9

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-8b

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-8b",
    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-8b",
    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-8b",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: deepseek-r1-distill-llama-8b

Provider: openrouter

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

Create API Key

Related Models

Similar models from openrouter

deepseek-r1-distill-llama-8b

deepseek-r1-distill-llama-8b

Access deepseek-r1-distill-llama-8b 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-8b by openrouter - AI Model Details, Pricing, and Performance Metrics

deepseek-r1-distill-llama-8b

deepseek-r1-distill-llama-8b

Access deepseek-r1-distill-llama-8b 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