DeepSeek Reasoner V3.1 API

deepseek/deepseek-r1
DeepSeek Reasoner V3.
Context
128K tokens
Input
$0.6877 / 1M tokens
Output
$2.95711 / 1M tokens

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.

DeepSeek Reasoner V3.1 API Pricing

TypePrice
Input
$0.6877 / 1M tokens
Output
$2.95711 / 1M tokens
Cached input
$0.6877 / 1M tokens

DeepSeek Reasoner V3.1 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Humanity's Last Exam
15.9%
Expert-level questions across many domainsSourceJuly 12, 2026
LiveCodeBench
74.8%
Contamination-free competitive programming problemsSourceJuly 12, 2026
GPQA Diamond
80.1%
Google-proof graduate science questions (hardest subset)SourceJuly 12, 2026
AIME 2025
88.4%
Competition mathematics (AIME), 2025SourceJuly 12, 2026
Intelligence
13.1
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Math
76
Composite score across standardised mathematics evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

DeepSeek Reasoner V3.1 vs other models

ModelInputOutputContextBest for
$0.6877 / 1M tokens
$2.95711 / 1M tokens
128K tokens
Chat + assistants
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

DeepSeek Reasoner V3.1 has a 128,000 tokens context window and can return up to 64,000 tokens.

DeepSeek Reasoner V3.1 takes text as input and returns text.

Use deepseek/deepseek-r1 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

DeepSeek Reasoner V3.1 is priced at input $0.6877 / 1M tokens, output $2.95711 / 1M tokens, cached input $0.6877 / 1M tokens.

Yes, DeepSeek Reasoner V3.1 can stream responses as they are generated.

DeepSeek Reasoner V3.1 was built by DeepSeek.

It is designed for reasoning-heavy tasks that benefit from chain-of-thought processing before generating a response.

Start building with DeepSeek Reasoner V3.1

Get API Key
1000+ models, one API.