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: 1,048,576 tokens
• Input: text
• Output: text
• Pricing: $0.09/M input tokens, $0.18/M output tokens

View on OpenRouter. Model data sourced from OpenRouter.