Yi Lightning
Active Parameters
100B (Estimated)
Context Length
32K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Proprietary
Release Date
20 Aug 2025
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.50 · Output: $2.00
Evaluation Benchmarks
Rank
#143
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1328 | 139 |
Coding Archived | 0.13 | 21 |
Rankings
Overall Rank
#143
Coding Rank
-
About Yi Lightning
01.AI's Yi Lightning model optimized for ultra-fast inference with strong multilingual capabilities. Features exceptional performance on Chinese and English with efficient architecture enabling low-latency responses. Ideal for applications requiring quick turnaround times such as conversational AI, real-time translation, and interactive applications. Maintains quality output while prioritizing speed and throughput.
Technical Specifications
Architecture specifications are undisclosed for proprietary models.
Resources
About Yi Lightning
01.AI's Yi Lightning series delivers fast inference with strong multilingual capabilities, particularly for Chinese and English. Optimized for low-latency applications requiring quick response times while maintaining quality reasoning and generation.
Other Yi Lightning Models
- No related models available