DeepSeek V4 ProPricing
Input Modalities
- Text
Output Modalities
- Text
Context length
- 1M tokens
Capabilities
- Thinking
- Streaming
- Tool calling
- Web search
- URL context
- Code interpreter
- Computer use
- File search
- Memory tool
- Structured outputs
- Citations
- Prompt caching
- Background mode
- Server-side sessions
Providers
Performance for deepseek-v4-pro
Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).
Try this model
Frequently asked questions
Compare DeepSeek V4 Pro
More models from DeepSeek
See all DeepSeek models →DeepSeek-V3.2-Exp
DeepSeek-V3.2-Exp
The model DeepSeek-V3.2-Exp is officially named deepseek-chat on the website. It is an experimental version. As an intermediate step towards the next-generation architecture, V3.2-Exp introduces DeepSeek Sparse Attention (a sparse attention mechanism) based on V3.1-Terminus, exploring and validating
DeepSeek V3.2 is DeepSeek's text large language model, designed for reasoning tasks and agentic tool use. It harmonizes high computational efficiency with strong reasoning performance through DeepSeek Sparse Attention (DSA), while providing native support for tools, function calling, and structured outputs.
The model DeepSeek-V3.2-Exp is officially named deepseek-chat on the website. It is an experimental version. As an intermediate step towards the next-generation architecture, V3.2-Exp introduces DeepSeek Sparse Attention (a sparse attention mechanism) based on V3.1-Terminus, exploring and validating
The model DeepSeek-V3.2-Exp-Think is officially named deepseek-reasoner. It is an experimental version. As an intermediate step towards the next-generation architecture, V3.2-Exp introduces DeepSeek Sparse Attention (a sparse attention mechanism) based on V3.1-Terminus, exploring and validating exploratory optimizations for training and inference efficiency on long texts.
