DeepSeek V4 Pro 0813 (batch)
DeepSeek · Released Aug 2026
A frontier-class mixture-of-experts model from DeepSeek with a 1-million-token context window, optimized for batch processing.
- Strengths
- Handles very long documents and reasoning tasks at the scale of the V4 Pro line while being configured for batch workflows.
- Best for
- Batch jobs requiring long-context understanding, such as processing entire documents, codebases, or conversation histories in a single request.
- Limitations
- Batch-only availability means it's not suitable for real-time or interactive applications; the V4.1 Flash released in 2026-09 offers a smaller, faster alternative for many tasks.
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 — out —
- 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 |