Inception
Mercury 2
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Cheapest input
$0.25
$/MTok · models.dev
Cheapest output
$0.75
$/MTok
Context
128K
tokens
Offers
7
3 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestmercury-2 | Inception | $0.25 | $0.75 | $0.025 | 128K |
| models.devinception/mercury-2 | Kilo Gateway | $0.25 | $0.75 | $0.025 | 128K |
| models.devmercury-2 | NanoGPT | $0.25 | $0.75 | $0.025 | 128K |
| OpenRouterinception/mercury-2 | OpenRouter | $0.25 | $0.75 | $0.025 | 128K |
| models.devinception/mercury-2 | Vercel AI Gateway | $0.25 | $0.75 | $0.025 | 128K |
| LiteLLMmercury-2 | — | $0.25 | $0.75 | $0.025 | — |
| models.devmercury-2 | Venice AI | $0.3125 | $0.9375 | $0.0313 | 128K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- In: text
- Out: text
Knowledge cutoff: 2025-01-01Released: 2026-02-24Family: mercury
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence21.4
- AA coding31.1
- AA agentic9.6
Sources: Arena AI, Artificial Analysis. See /benchmarks.