DeepSeek V3.1
DeepSeek V3.1 on ZenLLM: $0.087 per 1M input and $0.33 per 1M output tokens, 65% under the official price. One API key, prompts never stored.
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
All models and prices