AI model comparison
Mercury 2 vs DeepSeek V3.1
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Inception
Mercury 2
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).
- Input / 1M
- $0.25
- Output / 1M
- $0.75
- Context
- 128K
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
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Mercury 2
1.1x cheaper for a typical chat
Higher intelligence score
Mercury 2
13.8 vs 13.7 on Artificial Analysis
Larger context window
DeepSeek V3.1
164K vs 128K tokens
Newer release
Mercury 2
Released March 4, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Mercury 213.8DeepSeek V3.113.7Coding index
Mercury 231.1DeepSeek V3.1Not availableAgentic index
Mercury 21.6DeepSeek V3.1Not availablePricing
Mercury 2 vs DeepSeek V3.1 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Mercury 2 | DeepSeek V3.1 |
|---|---|---|
| Input tokensPer 1M tokens | $0.25 | $0.25 |
| Output tokensPer 1M tokens | $0.75 | $0.95 |
| Cached input (read)Per 1M tokens | $0.03 | $0.13 |
| 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
Mercury 2$0.88DeepSeek V3.1$0.98Coding task
30K in, 4K out
Mercury 2$10.50$3.75 cachedDeepSeek V3.1$11.30$7.70 cachedLong document summary
150K in, 2K out
Mercury 2$39$5.25 cachedDeepSeek V3.1$39.40$21.40 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Mercury 2 | DeepSeek V3.1 |
|---|---|---|
| Context window | 128K tokens | 164K tokens |
| Max output | 50K tokens | 33K tokens |
| Input types | Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Medium, Low, None | Not available |
| Default reasoning effort | Medium | Not available |
| Release date | March 4, 2026 | August 21, 2025 |
Features
Supported features
API features available for each model.
| Metric | Mercury 2 | DeepSeek V3.1 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Not 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 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 R1
- DeepSeek V3.1 vs GLM 4.6V
Our take
Mercury 2 is 1.1x cheaper for a typical chat. Mercury 2 scores higher on the Artificial Analysis Intelligence Index (13.8 vs 13.7). DeepSeek V3.1 has the larger context window (164K vs 128K 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 Mercury 2 or DeepSeek V3.1 cheaper?
Mercury 2 is cheaper for a typical chat (2K input tokens and 500 output tokens). Mercury 2 costs $0.25 per 1M input tokens and $0.75 per 1M output tokens, while DeepSeek V3.1 costs $0.25 per 1M input tokens and $0.95 per 1M output tokens.
Which has a bigger context window, Mercury 2 or DeepSeek V3.1?
DeepSeek V3.1 supports up to 164K tokens of context, compared with 128K for Mercury 2.
Is Mercury 2 smarter than DeepSeek V3.1?
On the Artificial Analysis Intelligence Index, Mercury 2 scores 13.8 and DeepSeek V3.1 scores 13.7, putting Mercury 2 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Mercury 2 and DeepSeek V3.1 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mercury 2 and DeepSeek V3.1 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Mercury 2 and DeepSeek V3.1 at the same time. Compare the answers side by side and keep the best one.