Model details
DeepSeek-V4-Pro-EL
DeepSeek-V4-Pro-EL appears oriented toward complex text generation, analysis, and coding workflows that benefit from broad context and open-weight deployment. A secondary editorial description associates the underlying V4 Pro family with a very large 671-billion-parameter design, but it does not specifically verify this EL variant, so that figure should be treated as family-level context rather than a confirmed specification of the cataloged model.
The model is best suited to users who need a capable reasoning-oriented system for substantial documents, long-running technical work, or iterative development, while recognizing that the supplied evidence does not establish benchmark leadership or a documented training lineage. Open-weight availability may support self-hosting and customization, making it a practical option for teams prioritizing control, experimentation, and integration into existing workflows.
Quick Info
Powered by- Provider
- Poe
- Model key
- empiriolabs/deepseek-v4-pro-el
- Release date
- Apr 24, 2026
- Last updated
- May 2, 2026
- Input modalities
- Output modalities
- Capabilities
Cost
- Input token cost
- $1.67
- Output token cost
- $3.33
Limits
- Input tokens
- 1,000,000 tokens
- Output tokens
- 384,000 tokens
- Context window
- 1,000,000 tokens