Scan to join WeChat groupDeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813: a deepseek-thinking model from Volcengine, ~1M context
DeepSeek V4 Pro 0813 is a deepseek-thinking model from Volcengine (~1M context, input around $1.3359/1M tokens). Suitable for assistants, content generation, knowledge Q&A and business automation
starsCapabilities
codeFunction callingdata_objectStructured output
paymentsContext and pricing
Context limit1,000,000
Max output384,000
Input price$1.3359/ 1M tokens
Output price$4.00771/ 1M tokens
Cached input price$0.04453/ 1M tokens
descriptionOverview
Overview
DeepSeek V4 Pro 0813 is provided by Volcengine, model ID deepseek-v4-pro-ga-260813
Key specs
- Context: 1M tokens
- Max output: 384K tokens
- Input price: $1.3359/1M
- Output price: $4.00771/1M
Best for
Consider DeepSeek V4 Pro 0813 when comparing context length, pricing, multimodal support and relay availability
lightbulbUse cases
- Assistants and customer support
- Content generation and rewriting
- Knowledge Q&A and summarization
- Structured extraction
thumb_upStrengths
- Very long context (~1M), good for long documents and codebases
- Open weights, can be self-hosted
- High single-response output limit (~384K)
infoLimitations
- Pricing and availability vary by upstream and relay; verify with official docs and tests