DeepSeek V4.1 Flash
by AMD · family deepseek-flash · listed Oct 2026RTVW
October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache readfree
Cache write—
Against the market
On the record
- Model id
DeepSeek-V4.1-Flash- Context window
- 1.0M tokens
- Max output
- 384K tokens
- Input modalities
- text, image
- 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
- developer.amd.com.cn/radeon/tokenfactory
Back of the envelope
≈
Also listed at
- Alibaba Token Planfree in · free out
- SCNet Token Planfree in · free out
- Nvidiafree in · free out
- Alibaba Token Plan (China)free in · free out
- SenseNova (China)free in · free out
- engy$0.03 in · $0.12 out
- OpenRouter$0.045 in · $0.50 out
- Vercel AI Gateway$0.075 in · $0.30 out
- ZenMux$0.075 in · $0.30 out
- NanoGPT$0.09 in · $0.25 out
- CoreWeave$0.13 in · $0.65 out
- LLM Gateway$0.135 in · $0.54 out
- DevPass (LLM Gateway)$0.135 in · $0.54 out
- Standard Compute$0.14 in · $0.42 out
- ClinePass$0.15 in · $0.60 out