DeepSeek V4 Pro 0813 (batch)
DeepSeek · Released Aug 2026
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model and the general availability release of DeepSeek V4 Pro, with a 1-million-token context window.
- Strengths
- It handles frontier-class reasoning and generation tasks with a very large context window that supports long-form documents and multi-turn conversations.
- Best for
- Production workloads requiring high reasoning capability and the ability to process extended context without truncation.
- Limitations
- As a larger frontier model, it is slower and more resource-intensive than DeepSeek V4 Flash, making it less suitable for latency-sensitive or cost-constrained applications.
Input / 1M
$0.66
Output / 1M
$1.98
Cached input / 1M
$0.022
Context window
1.05M
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 50.0% out decreased 50.0%
- 90d
- in decreased 50.0% out decreased 50.0%
- 1y
- in decreased 50.0% out decreased 50.0%
- Since launch
- in decreased 50.0% out decreased 50.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 8 Sep 2026 | $0.66 | $1.98 | $0.022 | Imported from OpenRouter | openrouter.ai |
| 29 Aug 2026 | $1.32 | $3.96 | $0.13 | Imported from OpenRouter | openrouter.ai |