AI model comparison
DeepSeek V3.1 vs R1
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
DeepSeek
DeepSeek V3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.
- Input / 1M
- $0.25
- Output / 1M
- $0.95
- Context
- 164K
DeepSeek
R1
DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens.
- Input / 1M
- $0.70
- Output / 1M
- $2.50
- Context
- 64K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
DeepSeek V3.1
2.7x cheaper for a typical chat
Higher intelligence score
DeepSeek V3.1
13.7 vs 11.4 on Artificial Analysis
Larger context window
DeepSeek V3.1
164K vs 64K tokens
Newer release
DeepSeek V3.1
Released August 21, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
DeepSeek V3.113.7R111.4Coding index
DeepSeek V3.1Not availableR124.6Agentic index
DeepSeek V3.1Not availableR11.1Pricing
DeepSeek V3.1 vs R1 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | DeepSeek V3.1 | R1 |
|---|---|---|
| Input tokensPer 1M tokens | $0.25 | $0.70 |
| Output tokensPer 1M tokens | $0.95 | $2.50 |
| Cached input (read)Per 1M tokens | $0.13 | Not available |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
DeepSeek V3.1$0.98R1$2.65Coding task
30K in, 4K out
DeepSeek V3.1$11.30$7.70 cachedR1$31Long document summary
150K in, 2K out
DeepSeek V3.1$39.40$21.40 cachedR1$110Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | DeepSeek V3.1 | R1 |
|---|---|---|
| Context window | 164K tokens | 64K tokens |
| Max output | 33K tokens | 16K tokens |
| Input types | Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | August 21, 2025 | January 20, 2025 |
Features
Supported features
API features available for each model.
| Metric | DeepSeek V3.1 | R1 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Not supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
DeepSeek V3.1View full model details- DeepSeek V3.1 vs Gemini 3.1 Flash Lite
- DeepSeek V3.1 vs Gemma 4 31B
- DeepSeek V3.1 vs GPT-5 Nano
- DeepSeek V3.1 vs Qwen3 235B A22B Instruct 2507
- DeepSeek V3.1 vs DeepSeek V3.2 Exp
- DeepSeek V3.1 vs DeepSeek V3 0324
- DeepSeek V3.1 vs GLM 4.7 Flash
- DeepSeek V3.1 vs DeepSeek V3.1 Terminus
- DeepSeek V3.1 vs Mercury 2
- DeepSeek V3.1 vs Nova 2 Lite
- DeepSeek V3.1 vs R1 0528
- DeepSeek V3.1 vs Nemotron 3 Super
- DeepSeek V3.1 vs Qwen3 Coder 480B A35B
- DeepSeek V3.1 vs GLM 4.6V
Our take
DeepSeek V3.1 is 2.7x cheaper for a typical chat. DeepSeek V3.1 scores higher on the Artificial Analysis Intelligence Index (13.7 vs 11.4). DeepSeek V3.1 has the larger context window (164K vs 64K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is DeepSeek V3.1 or R1 cheaper?
DeepSeek V3.1 is cheaper for a typical chat (2K input tokens and 500 output tokens). DeepSeek V3.1 costs $0.25 per 1M input tokens and $0.95 per 1M output tokens, while R1 costs $0.70 per 1M input tokens and $2.50 per 1M output tokens.
Which has a bigger context window, DeepSeek V3.1 or R1?
DeepSeek V3.1 supports up to 164K tokens of context, compared with 64K for R1.
Is DeepSeek V3.1 smarter than R1?
On the Artificial Analysis Intelligence Index, DeepSeek V3.1 scores 13.7 and R1 scores 11.4, putting DeepSeek V3.1 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use DeepSeek V3.1 and R1 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see DeepSeek V3.1 and R1 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to DeepSeek V3.1 and R1 at the same time. Compare the answers side by side and keep the best one.