Mercury 2
by Inception · inception/mercury-2 · #97 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:40 AM UTC · refreshed hourly
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.25
per 1M tokens
Output
$0.75
per 1M tokens
Blended (3:1)
$0.375
3 input : 1 output
Cache read
$0.025
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Mercury 2 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.375 | $0.0263 | — |
| 50% | $0.291 | $0.015 | −43% |
| 90% | $0.223 | $0.006 | −77% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00035 | $0.35 |
| Document summary | 8,000 | 1,000 | $0.00275 | $2.75 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.009 | $9.00 |
| Long-context analysis | 150,000 | 5,000 | $0.0412 | $41.25 |
Performance
Intelligence Index
21.4
AA composite quality
Coding Index
31.1
Math Index
—
Agentic Index
9.6
Output speed
1045 tok/s
median
Time to first token
3.40s
median
Time to first answer
3.40s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 77.0% |
| Humanity's Last Exam | 15.5% |
| SciCode | 38.7% |
| IFBench | 69.8% |
| AA-LCR (Long Context Reasoning) | 36.3% |
| Terminal-Bench Hard | 26.5% |
| Terminal-Bench 2.1 | 27.3% |
| τ²-Bench (Telecom) | 70.8% |
| τ³-Bench Banking | 9.9% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,014 |
| UI components | 1,013 |
| Data viz | 1,011 |
| SVG | 1,024 |
| 3D | 1,043 |
| Game dev | 1,036 |
| Code categories | 1,025 |
| ASCII art | 1,046 |
Specs
Context window
128K
tokens
Max output
50K
tokens
Input modalities
text
Tokenizer
Other