DeepSeek V4.1 Flash repriced across 2 hosts: DekaLLM output down 40%, input up 275%
Published 25 September 2026
Price move, per 1M tokens
- DekaLLM · input↑ 275%$0.040 → $0.150
- DekaLLM · output↓ 40%$1.00 → $0.60
- DekaLLM · cache read↓ 50%$0.010 → $0.005
- NextBit · input↓ 30%$0.30 → $0.21
- NextBit · output↓ 30%$1.20 → $0.84
- NextBit · cache read↓ 33%$0.006 → $0.004
| host | rate | was | now | change |
|---|---|---|---|---|
| DekaLLM | input | $0.040 | $0.150 | ↑ 275% |
| DekaLLM | output | $1.00 | $0.60 | ↓ 40% |
| DekaLLM | cache read | $0.010 | $0.005 | ↓ 50% |
| NextBit | input | $0.30 | $0.21 | ↓ 30% |
| NextBit | output | $1.20 | $0.84 | ↓ 30% |
| NextBit | cache read | $0.006 | $0.004 | ↓ 33% |
DekaLLM output: ↓ 40%DekaLLM input: ↑ 275%NextBit input and output: ↓ 30%
If you buy
On DekaLLM, this now suits output-heavy and cache-reliant work far more than prompt-heavy jobs, so re-check your input-to-output mix before your next top-up.
The model
DeepSeek V4.1 Flashopen the model →
Open weights763.2B parameters1049K context35 hosts
intelligence21st of 168 writing37th of 168 coding11th of 168 agents13th of 55
DeepSeek V4.1 Flash is a downloadable model with a permissive licence, and it places 11th of 168 on Arena Coding via Max as of 25 Sep 2026. At 763.2 billion parameters it is a data-centre job to run yourself, so hosted use is the practical route for most readers.
Source
Read on openrouter.ai · we published this on 25 September 2026.
read the original at openrouter.ai ↗