DeepSeek-R1

Model IntroductionText

DeepSeek-R1: General reasoning enhanced, chain-of-thought

DeepSeek-R1 is part of the DeepSeek lineup from DeepSeek, designed for production workloads that need reliable quality at scale. General reasoning enhanced, chain-of-thought.

It accepts Text inputs and produces Text outputs, with a context window of up to 128,000 input / 65,536 output tokens. The model is tuned for chat, analysis, and tool use in enterprise pipelines.

Extended chain-of-thought reasoning helps on math, logic, and multi-step planning. Use higher reasoning effort when accuracy matters more than latency.

Benchmarks

Benchmark (Area)Score*
AIME 2024 (Math)89.9% accuracy (Max)
LiveCodeBench (Coding)85.2 Pass@1 (Max)
Codeforces Rating (Coding)2838 rating (Max)
SWE-bench Verified (Coding)73.5% resolved (Max)
MMLU-Pro (Knowledge)80.2 EM (Max)
HMMT 2024 Feb (Math)88.2 Pass@1 (Max)
GPQA Diamond (Science)81.9 Pass@1 (Max)
MRCR 1M (Long Context)73.2 MMR (Max)
Terminal Bench 2.0 (Agent)52.9 Acc (Max)
Apex Shortlist (Agent)79.7 Pass@1 (Max)
Chinese-SimpleQA (Chinese)73.4 Pass@1 (Max)
SuperCLUE (Chinese)64.00 overall (Max)

API request example

Endpoint /v1/chat/completions. Replace <API_KEY> with a key from the console.

Standard OpenAI Chat Completions. Swap `model` for the target slug.

curl https://api.ravenrouter.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
  "model": "DeepSeek-R1",
  "messages": [
    {
      "role": "user",
      "content": "Hello! Introduce yourself in one sentence."
    }
  ],
  "max_tokens": 64
}'

More models: API Reference → Examples by model

DeepSeek-R1 API — $0.32/1M input, $1.29/1M output | RavenRouter AI