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.
by Deepseek|1M context|$0.09/M input tokens|$0.18/M output tokens
Endpoints
Available providers for this model, with details on pricing, context limits, and real-time health metrics.
