SOURCE-LINKED INTELLIGENCE
DeepSeek: DeepSeek V4 Flash 0423
OpenRouter model catalogue · model · Publication date unknown
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Read original source ↗ Open in workspace
- recordType
- model-catalog
- evidenceStatus
- provider-reported
- region
- Global
Evidence & attribution
First collected: 2026-09-20T08:01:03.945Z. This is not the publication date.
Observed changes
AIIC observation times, not verified publisher revision times. Up to eight recent revisions.
2026-09-27T17:11:28.120Z
- pricing:
{"input":0.047040000000000005,"output":0.09408000000000001} → {"input":0.046900000000000004,"output":0.09380000000000001}
2026-09-26T17:02:25.186Z
- pricing:
{"input":0.04816,"output":0.09632} → {"input":0.047040000000000005,"output":0.09408000000000001}
2026-09-25T16:43:16.188Z
- pricing:
{"input":0.08092,"output":0.16184} → {"input":0.04816,"output":0.09632}
2026-09-24T16:33:37.154Z
- pricing:
{"input":0.08245999999999999,"output":0.16491999999999998} → {"input":0.08092,"output":0.16184}
2026-09-23T16:31:38.658Z
- pricing:
{"input":0.049,"output":0.098} → {"input":0.08245999999999999,"output":0.16491999999999998}
2026-09-22T16:21:35.584Z
- pricing:
{"input":0.088606,"output":0.177212} → {"input":0.049,"output":0.098}
2026-09-21T08:02:06.831Z
- pricing:
{"input":0.036680000000000004,"output":0.07336000000000001} → {"input":0.088606,"output":0.177212}