DeepSeek V4 Flash 0423 vs Inception Mercury 2.5
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Mercury 2.5 is 1.7× cheaper at a typical mix of 3 input tokens per output token.
- DeepSeek V4 Flash 0423 accepts longer prompts: 1M vs 260K tokens.
- DeepSeek V4 Flash 0423 output costs $0.081 per 1M via Baidu, against the list price of $0.182.
- Mercury 2.5 is the newer model (released 2026-09-08).
| DeepSeek V4 Flash 0423 | Mercury 2.5 | |
|---|---|---|
| Vendor | DeepSeek | Inception |
| Released | 2026-04-24 | 2026-09-08 |
| Input / 1M | $0.091 | $0.04 |
| Output / 1M | $0.182 | $0.15 |
| Cached input / 1M | $0.018 | $0.0040 |
| Blended / 1M (3:1) | $0.114 | $0.068 |
| Context | 1M | 260K |
| Max output | 944K | 66K |
| Accepts | text | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 17 | 1 |
| Cheapest provider, output | $0.081 | $0.15 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
DeepSeek V4 Flash 0423
$8.19 per month$0.27 per day
Mercury 2.5
$4.65 per month$0.15 per day
Mercury 2.5 saves $3.54 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare DeepSeek V4 Flash 0423 with