DeepSeek R1

Featured Latest
DeepSeek DeepSeek R1 Generally Available Jan 2025

DeepSeek's open-weight reasoning model. Matches o1 on math and science benchmarks with visible chain-of-thought, MIT licence, and 13K+ HuggingFace likes — the most-downloaded open reasoning model.

Context
128K
tokens
Input
$1.35
per MTok
Output
$5.40
per MTok

About

DeepSeek-R1 — AI tool

Modalities

Input
Text Code
Output
Text Code

Code Examples

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-R1",
    "messages": [
      { "role": "user", "content": "Explain quantum entanglement in one sentence." }
    ]
  }'

API Parameters

Name Type Description
frequency_penalty number Penalize tokens by their frequency so far. Positive values reduce repetition.
max_completion_tokens integer Maximum number of tokens the model may generate in the response.
presence_penalty number Penalize tokens that have appeared at all so far. Positive values encourage new topics.
response_format one of Constrain output to a JSON schema or an enum (structured outputs).
seed integer Deterministic seed for sampling. Same seed + same prompt produces identical output.
stop array Up to 4 sequences where the API will stop generating tokens.
stream boolean Stream partial responses as Server-Sent Events.
temperature number Sampling temperature; higher values produce more random output. 0 is deterministic.
tool_choice one of Controls which (if any) tool is called: "none", "auto", "required", or a specific tool.
tools array List of tools (functions) the model may call.
top_p number Nucleus sampling: consider only tokens whose cumulative probability ≥ top_p.

Standard OpenAI-compatible parameters. Consult the provider docs for model-specific behaviour.

Benchmark Scores

Benchmark Score
MMLU 84.9%
MATH-500 97.3%
GPQA Diamond 71.5%
HumanEval 92.9%
SWE-bench Verified 49.2%

Performance

30
tok / sec
output speed

Source: DeepSeek R1 paper + Artificial Analysis, April 2026

Strengths & Limitations

Best For
Open-weight reasoning model with visible CoT
o1-level math and science
MIT licence
13K HuggingFace likes / 3.5M downloads
Distilled smaller variants available (7B–70B)
Limitations
Large 671B total deployment requirement
No vision modality
Longer latency due to reasoning steps
No tool/function calling

Tags

Open WeightsReasoningThinkingMathCodingMoE