DeepSeek V4 Flash
DeepSeek V4 Flash on ZenLLM: $0.056 per 1M input and $0.11 per 1M output tokens, 38% under the official price. One API key, prompts never stored.
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
All models and prices