deepseek
DeepSeek: DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
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.
- Context window: 1,310,720 tokens
- Input: text
- Output: text
- Pricing: $0.04/M input tokens, $0.16/M output tokens
RuntimeWire coverage
- OneTriangle launches DeepSeek V4 Flash hosting at $0.15 per million input tokens
- Ornith AI ships open models that write their own training curriculum
- Head to head: DeepSeek-V4-Flash-0731 vs Phi-4
- Head to head: DeepSeek-V4-Flash-0731 vs gpt-oss-120b
- Open-weight models surge past closed rivals in Vercel token traffic
- ARC Prize verifies DeepSeek V4 Flash at 61.4% for $0.04 per task
- CostPerPrompt publishes calculators for estimating monthly AI application costs
- DeepSeek ships V4 Flash with strong agent scores and low API prices
View on OpenRouter. Model data sourced from OpenRouter.