DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 on ZenLLM: $0.011 per 1M input and $0.065 per 1M output tokens, 82% under the official price. One API key, prompts never stored.
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....
All models and prices