DeepSeek V4.1 Flash 1017
by Refuseless · family deepseek-flash · listed Oct 2026RTW
October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
Current rates USD per 1M tokens
Input$0.01
Output$0.08
Cache read$0.002
Cache write—
Against the market
On the record
- Model id
deepseek-v4.1-flash-fast- Context window
- 1.0M tokens
- Max output
- 262K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- May 2025
- Released
- 2026-10-17
- Last updated
- 2026-10-17
- Provider docs
- docs.refuseless.com/models
Back of the envelope
≈
Also listed at
- CommandCode$0.16 in · $0.58 out
- LithosAI$0.25 in · $2.00 out
- CoralBricks$0.25 in · $1.20 out
- Wally$0.275 in · $1.20 out
- Baseten$0.60 in · $2.40 out
- Vercel AI Gateway$0.60 in · $2.40 out
- Kilo Gateway$0.60 in · $2.40 out