R1
VerifiedDeepSeek R1 handles massive text contexts as an open LLM.
About R1
R1 was developed by DeepSeek as an open-weight LLM, granting users complete access to its architecture for research and modification. Its standout design element is the 163840-token context window that accommodates very long input sequences. This enables coherent processing across extended documents or conversations.
Strengths include reliable handling of large-scale text without truncation issues common in smaller-context models. Typical usage covers long-form content analysis, multi-turn dialogue systems, and tasks requiring retention of distant information. Developers often deploy it in environments where transparency and custom adaptation are priorities.
Capabilities
Benchmarks & performance
Independent evaluation scores and measured speed.
Source: Artificial Analysis
How R1 compares
R1 (striped bar) vs other language models on intelligence, speed and price.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · R1 ranks #33 of 67
Price
USD per 1M output tokens · Lower is better · R1 ranks #116 of 141
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long mathematical derivations
The model applies step-by-step logical deduction to solve advanced math problems that require extended reasoning chains.
Large-scale code generation
It produces and refines code across repositories that fit within its 163840-token context window.
Technical document analysis
R1 processes lengthy technical texts while strictly following complex instructions for accurate extraction and summarization.
Strengths & limitations
Strengths
- +Strong performance on complex reasoning tasks
- +Effective use of very large context windows
- +Clear structured outputs for technical problems
- +Solid coding and math capabilities
Limitations
- –Text-only modality with no vision support
- –May struggle with real-time or post-training knowledge
- –Large context can increase computational cost
Cost calculator
Estimate what R1 would cost for your usage.
Based on R1's $0.70/1M input · $2.50/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "deepseek/deepseek-r1",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: deepseek/deepseek-r1
Editor's verdict
R1 is DeepSeek's open-weight language models with a 164K-token context window.
On independent testing it scores 27.1 on the Artificial Analysis Intelligence Index.
At $2.50 per 1M output tokens, it is mid-priced for its class.
As an open-weight model you can self-host it or call it through a hosted API.
Best suited to strong performance on complex reasoning tasks and effective use of very large context windows.
Frequently asked questions
R1 provides a context window of 163840 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other R models
Sibling versions in the R family from DeepSeek.
Similar models
Other language models worth comparing.