DeepSeek V4.1 Flash 1017 vs LiquidAI LFM2.5-24B-A2B
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
- LFM2.5-24B-A2B is 1.2× cheaper at a typical mix of 3 input tokens per output token.
- DeepSeek V4.1 Flash 1017 accepts longer prompts: 1M vs 128K tokens.
- DeepSeek V4.1 Flash 1017 output costs $0.15 per 1M via Sail Research, against the list price of $0.60.
| DeepSeek V4.1 Flash 1017 | LFM2.5-24B-A2B | |
|---|---|---|
| Vendor | DeepSeek | LiquidAI |
| Released | 2026-10-17 | 2026-10-13 |
| Input / 1M | $0.15 | $0.05 |
| Output / 1M | $0.60 | $0.70 |
| Cached input / 1M | $0.0030 | $0.025 |
| Blended / 1M (3:1) | $0.262 | $0.212 |
| Context | 1M | 128K |
| Max output | 393K | 8K |
| Accepts | text, image | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 37 | 1 |
| Cheapest provider, output | $0.15 | $0.70 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
DeepSeek V4.1 Flash 1017
$18.00 per month$0.60 per day
LFM2.5-24B-A2B
$13.50 per month$0.45 per day
LFM2.5-24B-A2B saves $4.50 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare DeepSeek V4.1 Flash 1017 with