Context
128K
Max output
50K
Serving providers
2
Cheapest input
$0.25 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
939 t/s
tokens / second
Time to first token
3.44s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 1% | default | — | |
| GDPval | 697.7 | default | — | |
| GPQA Diamond | 77% | default | — | |
| Humanity's Last Exam | 17% | default | — | |
| IFBench | 70% | default | — | |
| Long-Context Reasoning | 41% | default | — | |
| Omniscience | -50.7 | default | — | |
| Omniscience Accuracy | 0.2 | default | — | |
| Omniscience Non Hallucination | 0.1 | default | — | |
| SciCode | 39% | default | — | |
| TerminalBench Hard | 27% | default | — | |
| TerminalBench v2.1 | 27% | default | — | |
| τ-bench Banking | 9% | default | — | |
| τ²-bench | 71% | default | — |
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| InceptionCheapest | $0.25 | $0.75 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| OpenRouterCheapest | $0.25 | $0.75 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$110
estimated / month
Model IDs
copy the exact identifier for your platforminception/mercury-2inception/mercury-2
Frequently asked questions
Mercury 2 pricing, context and availabilityHow much does Mercury 2 cost?
Mercury 2 costs $0.25 per 1M input tokens and $0.75 per 1M output tokens at its cheapest provider via Inception.
What is the context window of Mercury 2?
Mercury 2 accepts up to 128K tokens of context and can return up to 50K output tokens.
Which providers serve Mercury 2?
Mercury 2 is available from 2 serving providers, each with its own pricing and model ID. Inception is currently the cheapest.
What can Mercury 2 do?
Mercury 2 supports tool use, prompt caching and structured output.
Other Inception models
compare pricing across the Inception lineupPopular comparisons
head-to-head pages featuring Mercury 2
Mercury 2 vs Claude Fable 5side-by-side pricing & benchmarks Mercury 2 vs Claude Opus 4.8side-by-side pricing & benchmarks Mercury 2 vs Claude Sonnet 5side-by-side pricing & benchmarks
Mercury 2 vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
Mercury 2 vs Gemini 3.1 Pro Previewside-by-side pricing & benchmarks Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI