Inception
Mercury 2
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).
At a glance
- Input / 1M
- $0.25
- Output / 1M
- $0.75
- Context
- 128K
- Max output
- 50K
- Intelligence
- 13.8
- Released
- Mar 2026
Pricing
Mercury 2 API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.25 |
|---|---|
| Output tokensPer 1M tokens | $0.75 |
| Cached input (read)Per 1M tokens | $0.03 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.88
per 1,000 requests
Coding task
30K in, 4K out
$10.50
per 1,000 requests
Long document summary
150K in, 2K out
$39
per 1,000 requests
Benchmarks
Mercury 2 benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
13.8
Coding index
31.1
Agentic index
1.6
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 128K tokens
- Max output
- 50K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- High, Medium, Low, None
- Release date
- March 4, 2026
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Mercury 2 vs other models
See how Mercury 2 stacks up head to head on price, benchmarks, and features.
VS
Mercury 2 vs Gemini 3.1 Flash Lite
Inception vs Google
See comparisonVS
Mercury 2 vs DeepSeek V3.1 Terminus
Inception vs DeepSeek
See comparisonVSMercury 2 vs Gemma 4 31B
Inception vs Google
See comparisonVSMercury 2 vs DeepSeek V3.1
Inception vs DeepSeek
See comparisonVS
Mercury 2 vs GPT-5 Nano
Inception vs OpenAI
See comparisonVSMercury 2 vs Nemotron 3 Super
Inception vs NVIDIA
See comparisonAlternatives
Mercury 2 alternatives
Similar models worth considering, and where each one has the edge.
Gemini 3.1 Flash Lite
DeepSeek
DeepSeek V3.1 Terminus
Gemma 4 31B
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Mercury 2 cost?
Mercury 2 costs $0.25 per 1M input tokens and $0.75 per 1M output tokens through the API. A typical chat message costs about $0.88 per 1,000 messages.
What is the context window of Mercury 2?
Mercury 2 accepts up to 128K tokens of input and can write up to 50K tokens in a single response.
What is the best alternative to Mercury 2?
Gemini 3.1 Flash Lite from Google is a strong alternative. It offers: higher intelligence score, larger 1.05m context, accepts image and video and file and audio.
Can I use Mercury 2 alongside other models?
Yes. Shortcut Chat sends one prompt to Mercury 2 and any other models you pick at the same time, so you can compare answers side by side.
Try Mercury 2 next to every other model.
Use Mercury 2 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.