deepseek-r1

completions

On:fireworksaideepinfra

deepseek-r1

completions

Published by: deepseekProviders:

fireworksai deepinfra

DeepSeek-Reasoner is an advanced AI model designed to enhance logical reasoning and problem-solving capabilities, leveraging deep learning techniques to provide accurate and contextually relevant insights across various domains.

Provider	Input	Output
fireworksai	$8 / 1M tokens	$8 / 1M tokens
deepinfra	$0.75 / 1M tokens	$2.4 / 1M tokens

Released

Jan 20, 2025

Knowledge

Jul 24, 2024

Context

160K

Input

$8 / 1M tokens

Output

$8 / 1M tokens

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats	License
fireworksai	160K tokens	$8 / 1M tokens	$8 / 1M tokens	text	text	MIT
deepinfra	16K tokens	$0.75 / 1M tokens	$2.4 / 1M tokens	text	text	MIT

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

Access deepseek-r1 through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-r1 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 deepseek-r1

Category Performance Scores:

Academia: Score 66.65 (Top 6% - Rank #21)
Finance: Score 64.00 (Top 13% - Rank #45)
Marketing: Score 58.78 (Top 12% - Rank #42)
Maths: Score 76.00 (Top 13% - Rank #45)
Programming: Score 58.70 (Top 3% - Rank #11)
Science: Score 75.32 (Top 8% - Rank #28)
Writing: Score 58.48 (Top 16% - Rank #56)

Overall Performance: 65.41960317460317 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	89.30	Top 3%	Mathematics
AA Coding Index	58.70	Top 3%	Programming
AAII	52.00	Top 7%	General
AA Math Index	76.00	Top 13%	Mathematics
GPQA	81.30	Top 5%	STEM (Physics, Chemistry, Biology)
HLE	14.90	Top 6%	General Knowledge
LiveCodeBench	77.00	Top 3%	Programming
MATH-500	98.30	Top 3%	Mathematics
MMLU-Pro	84.90	Top 5%	General Knowledge
SciCode	40.30	Top 4%	Scientific

GPQA Score: 81.30 - Graduate-level reasoning benchmark

Model Comparison:

Provider: fireworksai

Model Type: completions

Context Size: 160000 tokens

Comparing against 345 models in the database

Performance Analytics for deepseek-r1

Usage Statistics (Last 1 Days):

Total Requests: 9 API calls
Average TPS: 655.81 tokens per second
Average Response Time: 8755.30ms
Average Time to First Token: 768.00ms
Total Cost: $0.50
Average Request Cost: $0.0551

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/19/2025	9	655.81	8755.30ms	768.00ms	$0.50

Performance Summary:

Model: deepseek-r1 by fireworksai

Monitoring Period: 9/13/2025 to 9/20/2025

Average Daily Requests: 9

Peak Daily Requests: 9

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

655.81 tokens/s

Category Scores

programming#6

Benchmark Tests

View Other Benchmarks

AIME

89.3

Mathematics

AA Coding Index

58.7

Programming

AAII

52.0

General

AA Math Index

76.0

Mathematics

GPQA

81.3

STEM (Physics, Chemistry, Biology)

HLE

14.9

General Knowledge

LiveCodeBench

77.0

Programming

MATH-500

98.3

Mathematics

MMLU-Pro

84.9

General Knowledge

SciCode

40.3

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	89.3	58.7	52.0	76.0	81.3	14.9	77.0	98.3	84.9	40.3

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for deepseek-r1

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

Model: deepseek-r1

Provider: fireworksai

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

Create API Key

Related Models

Similar models from fireworksai

deepseek-r1

deepseek-r1

Access deepseek-r1 through LangDB AI Gateway

Statistics

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-r1-05-28

deepseek-r1 by fireworksai - AI Model Details, Pricing, and Performance Metrics

deepseek-r1

deepseek-r1

Access deepseek-r1 through LangDB AI Gateway

Statistics

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-r1-05-28