DeepSeek: DeepSeek V4 PRO 0813
DeepSeek's large flagship model for demanding reasoning, coding and agentic work. Supports tool calling, adjustable reasoning effort and a context of up to one million tokens.
- Maker
- DeepSeek
- Model ID
deepseek/deepseek-v4-pro-0813- Context length
- 1,048,576 tokens
- Input
- text
- Output
- text
- Capabilities
- tool calling, structured output, and reasoning
Providers
- TensorX: Data centers: Ireland and Finland; Zero data retention
- Lyceum: Data centers: France, Finland, and Germany; Zero data retention
Facts as Markdown · Quickstart
More models by DeepSeek
- DeepSeek: DeepSeek V4 Flash 0731 DeepSeek · 256,000 tokens · text
- DeepSeek: DeepSeek V4.1 Flash DeepSeek · 1,048,576 tokens · text
- DeepSeek: DeepSeek V4.1 Flash 1017 DeepSeek · 1,048,576 tokens · text
More Text models
- Google: Gemma 4 26B A4B IT Google · 256,000 tokens · text
- Google: Gemma 4 31B IT Google · 262,144 tokens · text
- Meta: Llama 3.3 70B Instruct Meta · 131,072 tokens · text
- MiniMax: MiniMax M3 MiniMax · 1,048,576 tokens · text
- MiniMax: MiniMax M3.1 Flash MiniMax · 1,048,576 tokens · text
- Mistral AI: Codestral 2508 Mistral AI · 131,072 tokens · text