DeepSeek V4 Flash 0731
by Kilo Gateway · family deepseek-flash · listed Jul 2026RTW
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
Current rates USD per 1M tokens
Input$0.14
Output$0.28
Cache read$0.028
Cache write—
Against the market
On the record
- Model id
deepseek/deepseek-v4-flash-0731- Context window
- 1.0M tokens
- Max output
- 384K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- May 2025
- Released
- 2026-07-31
- Last updated
- 2026-07-31
- Provider docs
- kilo.ai
Back of the envelope
≈
Also listed at
- Alibaba Token Planfree in · free out
- Alibaba Token Plan (China)free in · free out
- DigitalOcean$0.08 in · $0.252 out
- OpenRouter$0.09 in · $0.18 out
- Deep Infra$0.09 in · $0.18 out
- CrofAI$0.12 in · $0.21 out
- Weights & Biases$0.13 in · $0.28 out
- Baseten$0.13 in · $0.26 out
- Fireworks AI$0.14 in · $0.28 out
- NanoGPT$0.14 in · $0.28 out
- Ambient$0.14 in · $0.28 out
- EmpirioLabs AI$0.14 in · $0.28 out
- Together AI$0.14 in · $0.28 out
- Requesty$0.14 in · $0.28 out
- Hugging Face$0.14 in · $0.28 out