Name: DeepSeek Reasoner V3.1 API
Brand: DeepSeek

Overview

What is DeepSeek Reasoner V3.1 API?

DeepSeek Reasoner V3.1 excels in reasoning tasks with advanced chain-of-thought processing and the latest improvements in parameter activation.

Technical Specifications
- Supported inputs: Text
- Output: Text
- Context window: 128,000 tokens / Max output: 64,000 tokens
- Endpoint: /chat/completions

Performance Benchmarks
[embed]

DeepSeek Reasoner V3.1 API Pricing
- Input: $0.65 / 1M tokens
- Output: $2.795 / 1M tokens

Where to Use DeepSeek Reasoner V3.1

Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.

Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.

Code Sample
[embed]

Uptime and performance

Uptime (24h): 100%
Uptime (7d): 100%
Availability (24h): 100%
Error rate (24h): 0%
End-to-end latency (24h median): 11.6s
Time to first token (24h median): 1.6s
Throughput (24h median): 14.5 tok/s

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

Software development: DeepSeek-R1 is documented as suitable for generating code snippets, debugging existing code, code reviews, and architecture planning.

Mathematics and scientific reasoning: It is documented as useful for complex math problem-solving, scientific reasoning, and other step-by-step reasoning tasks.

Content creation and summarization: It is documented as suited to generating written content, editing, and summarizing existing material, including long-document analysis and summarization.

Customer support and assistant workflows: It is documented as usable for customer service chatbots and for agent/workflow automation that requires multi-step planning and tool orchestration.

How to use DeepSeek Reasoner V3.1 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to deepseek/deepseek-r1.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "deepseek/deepseek-r1",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())

const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-r1",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());

curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-r1","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.