Mercury 2
AI model by Inception. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Mercury 2 is a budget-tier option from Inception at $0.75/M output tokens. Despite the low price, it scores competitively on Coding Index (31.1) and Intelligence Index (21.9) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Mercury 2 reports 835 tok/s output speed and 3930ms time-to-first-token. Output speed is in the top tier — usable for streamed interactive UIs.
Cost model. For a workload of 1M input tokens + 100K output tokens, Mercury 2 costs $0.33 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Mercury 2Current | $0.25 | $0.75 | 835 tok/s |
| Llama 3.3 Instruct 70B | $0.66 | $0.72 | 84 tok/s |
| Hermes 3 - Llama-3.1 70B | $0.70 | $0.70 | 34 tok/s |
| Qwen3 VL 8B Instruct | $0.18 | $0.70 | 107 tok/s |
| Mixtral 8x7B Instruct | $0.45 | $0.70 | — |
| Qwen3 VL 30B A3B Instruct | $0.20 | $0.80 | 109 tok/s |