AI model comparison
Mercury 2 vs GPT-4.1 Mini
Side by side comparison of Mercury 2 and GPT-4.1 Mini on pricing, benchmark scores, context window, and more.
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
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.
- Input / 1M
- $0.40
- Output / 1M
- $1.60
- Context
- 1.05M
Comparing image generators? Compare image models
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Mercury 2
1.8x cheaper for a typical chat
Higher intelligence score
Mercury 2
10.8 vs 10.2 on Artificial Analysis
Larger context window
GPT-4.1 Mini
1.05M 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 210.8GPT-4.1 Mini10.2Coding index
Mercury 231.1GPT-4.1 Mini20.2Agentic index
Mercury 21.6GPT-4.1 MiniNot availablePricing
Mercury 2 vs GPT-4.1 Mini API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Mercury 2 | GPT-4.1 Mini |
|---|---|---|
| Input tokensPer 1M tokens | $0.25 | $0.40 |
| Output tokensPer 1M tokens | $0.75 | $1.60 |
| Cached input (read)Per 1M tokens | $0.03 | $0.10 |
| Cache writePer 1M tokens | Not available | Not available |
| Web searchPer request | Not available | $0.01 |
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$0.88GPT-4.1 Mini$1.60Coding task
30K in, 4K out
Mercury 2$10.50$3.75 cachedGPT-4.1 Mini$18.40$9.40 cachedLong document summary
150K in, 2K out
Mercury 2$39$5.25 cachedGPT-4.1 Mini$63.20$18.20 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 | GPT-4.1 Mini |
|---|---|---|
| Context window | 128K tokens | 1.05M tokens |
| Max output | 50K tokens | 33K tokens |
| Input types | Text | File, Image, 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 | April 14, 2025 |
Features
Supported features
API features available for each model.
| Metric | Mercury 2 | GPT-4.1 Mini |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Not supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Not 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.
GPT-4.1 MiniView full model details- GPT-4.1 Mini vs gpt-oss-120b
- GPT-4.1 Mini vs Gemini 2.5 Flash Lite
- GPT-4.1 Mini vs GPT-4o-mini
- GPT-4.1 Mini vs GPT-5.6 Luna Pro
- GPT-4.1 Mini vs GPT-4.1
- GPT-4.1 Mini vs Qwen3 VL 235B A22B Instruct
- GPT-4.1 Mini vs DeepSeek V3 0324
- GPT-4.1 Mini vs Nemotron 3 Super
- GPT-4.1 Mini vs Qwen3 Next 80B A3B Instruct
- GPT-4.1 Mini vs GLM 4.5 Air
- GPT-4.1 Mini vs Command A+
- GPT-4.1 Mini vs Mistral Medium 3.1
- GPT-4.1 Mini vs Kimi K2 0711
- GPT-4.1 Mini vs o3 Mini
- GPT-4.1 Mini vs Sonar
- GPT-4.1 Mini vs MiniMax M1
- GPT-4.1 Mini vs GLM 4.6V
- GPT-4.1 Mini vs Qwen3 Next 80B A3B Thinking
- GPT-4.1 Mini vs GPT-4o (2024-08-06)
- GPT-4.1 Mini vs o3 Mini High
- GPT-4.1 Mini vs Devstral 2 2512
- GPT-4.1 Mini vs Mistral Large 3 2512
- GPT-4.1 Mini vs Mistral Medium 3
- GPT-4.1 Mini vs GPT-4o (2024-11-20)
- GPT-4.1 Mini vs GLM 4.5V
- GPT-4.1 Mini vs Hermes 4 405B
- GPT-4.1 Mini vs Nova Pro 1.0
Our take
Mercury 2 is 1.8x cheaper for a typical chat. Mercury 2 scores higher on the Artificial Analysis Intelligence Index (10.8 vs 10.2). GPT-4.1 Mini has the larger context window (1.05M 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 GPT-4.1 Mini 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 GPT-4.1 Mini costs $0.40 per 1M input tokens and $1.60 per 1M output tokens.
Which has a bigger context window, Mercury 2 or GPT-4.1 Mini?
GPT-4.1 Mini supports up to 1.05M tokens of context, compared with 128K for Mercury 2.
Is Mercury 2 smarter than GPT-4.1 Mini?
On the Artificial Analysis Intelligence Index, Mercury 2 scores 10.8 and GPT-4.1 Mini scores 10.2, 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 GPT-4.1 Mini at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mercury 2 and GPT-4.1 Mini answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Mercury 2 and GPT-4.1 Mini at the same time. Compare the answers side by side and keep the best one.