AI model comparison
Mercury 2.5 vs Mercury 2
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Inception
Mercury 2.5
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception.
- Input / 1M
- $0.04
- Output / 1M
- $0.15
- Context
- 260K
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
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Mercury 2.5
5.6x cheaper for a typical chat
Higher intelligence score
Mercury 2.5
12.3 vs 10.8 on Artificial Analysis
Larger context window
Mercury 2.5
260K vs 128K tokens
Newer release
Mercury 2.5
Released September 8, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Mercury 2.512.3Mercury 210.8Coding index
Mercury 2.5Not availableMercury 231.1Agentic index
Mercury 2.5Not availableMercury 21.6Pricing
Mercury 2.5 vs Mercury 2 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Mercury 2.5 | Mercury 2 |
|---|---|---|
| Input tokensPer 1M tokens | $0.04 | $0.25 |
| Output tokensPer 1M tokens | $0.15 | $0.75 |
| Cached input (read)Per 1M tokens | $0.00 | $0.03 |
| 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 2.5$0.16Mercury 2$0.88Coding task
30K in, 4K out
Mercury 2.5$1.80$0.72 cachedMercury 2$10.50$3.75 cachedLong document summary
150K in, 2K out
Mercury 2.5$6.30$0.90 cachedMercury 2$39$5.25 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Mercury 2.5 | Mercury 2 |
|---|---|---|
| Context window | 260K tokens | 128K tokens |
| Max output | 66K tokens | 50K tokens |
| Input types | Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Medium, Low, None | High, Medium, Low, None |
| Default reasoning effort | Medium | Medium |
| Release date | September 8, 2026 | March 4, 2026 |
Features
Supported features
API features available for each model.
| Metric | Mercury 2.5 | Mercury 2 |
|---|---|---|
| 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 | Not 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.
Mercury 2View full model details- Mercury 2 vs Gemini 2.5 Flash Lite
- Mercury 2 vs gpt-oss-120b
- Mercury 2 vs Qwen3 235B A22B Instruct 2507
- Mercury 2 vs Qwen3 Coder 480B A35B
- Mercury 2 vs Mistral Small 4
- Mercury 2 vs GLM 4.6V
- Mercury 2 vs GLM 4.5 Air
- Mercury 2 vs Trinity Large Thinking
- Mercury 2 vs Llama 4 Maverick
- Mercury 2 vs Qwen3 Coder Next
Our take
Mercury 2.5 is 5.6x cheaper for a typical chat. Mercury 2.5 scores higher on the Artificial Analysis Intelligence Index (12.3 vs 10.8). Mercury 2.5 has the larger context window (260K 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 2.5 or Mercury 2 cheaper?
Mercury 2.5 is cheaper for a typical chat (2K input tokens and 500 output tokens). Mercury 2.5 costs $0.04 per 1M input tokens and $0.15 per 1M output tokens, while Mercury 2 costs $0.25 per 1M input tokens and $0.75 per 1M output tokens.
Which has a bigger context window, Mercury 2.5 or Mercury 2?
Mercury 2.5 supports up to 260K tokens of context, compared with 128K for Mercury 2.
Is Mercury 2.5 smarter than Mercury 2?
On the Artificial Analysis Intelligence Index, Mercury 2.5 scores 12.3 and Mercury 2 scores 10.8, putting Mercury 2.5 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Mercury 2.5 and Mercury 2 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mercury 2.5 and Mercury 2 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Mercury 2.5 and Mercury 2 at the same time. Compare the answers side by side and keep the best one.