DeepSeek
R1
DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens.
At a glance
- Input / 1M
- $0.70
- Output / 1M
- $2.50
- Context
- 64K
- Max output
- 16K
- Intelligence
- 11.4
- Released
- Jan 2025
Pricing
R1 API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.70 |
|---|---|
| Output tokensPer 1M tokens | $2.50 |
| Cached input (read)Per 1M tokens | Not available |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$2.65
per 1,000 requests
Coding task
30K in, 4K out
$31
per 1,000 requests
Long document summary
150K in, 2K out
$110
per 1,000 requests
Benchmarks
R1 benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
11.4
Coding index
24.6
Agentic index
1.1
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 64K tokens
- Max output
- 16K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- January 20, 2025
- Knowledge cutoff
- July 31, 2024
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
R1 vs other models
See how R1 stacks up head to head on price, benchmarks, and features.
VS
R1 vs Gemini 2.5 Flash
DeepSeek vs Google
See comparisonVSR1 vs DeepSeek V3.1
DeepSeek vs DeepSeek
See comparisonVS
R1 vs Nova 2 Lite
DeepSeek vs Amazon
See comparisonVSR1 vs R1 0528
DeepSeek vs DeepSeek
See comparisonVSR1 vs GLM 4.5
DeepSeek vs Z.ai
See comparisonVSR1 vs Kimi K2 0711
DeepSeek vs Moonshot AI
See comparisonAlternatives
R1 alternatives
Similar models worth considering, and where each one has the edge.
Gemini 2.5 Flash
DeepSeek
DeepSeek V3.1
Amazon
Nova 2 Lite
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does R1 cost?
R1 costs $0.70 per 1M input tokens and $2.50 per 1M output tokens through the API. A typical chat message costs about $2.65 per 1,000 messages.
What is the context window of R1?
R1 accepts up to 64K tokens of input and can write up to 16K tokens in a single response.
What is the best alternative to R1?
Gemini 2.5 Flash from Google is a strong alternative. It offers: higher intelligence score, larger 1.05m context, accepts file and image and audio and video.
Can I use R1 alongside other models?
Yes. Shortcut Chat sends one prompt to R1 and any other models you pick at the same time, so you can compare answers side by side.
Try R1 next to every other model.
Use R1 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.