November 2025
Chat Model
NGen 3.5 Lite
Efficient conversational intelligence for high-volume product and support workflows.
Overview
NGen 3.5 Lite provides efficient and fast conversational AI capabilities, optimized for applications that need quick response times, low operating cost, and steady everyday reasoning quality.
Context & Specs
Context Length
128,000 tokens
Model Priority
Low-latency chat
Best For
Support flows, product assistants, high-volume messaging, and lightweight content tasks.
Pricing
Rs 0.30 input / Rs 0.45 output per 1K tokens
Key Capabilities
- Fast and efficient conversational model for repeated production use.
- Optimized for quick response times across common chat and support workloads.
- Cost-effective profile for high-volume applications.
- Balanced performance across knowledge, reasoning, and instruction-following tasks.
Performance Benchmarks
| Category | Benchmark | Score | Industry Avg. |
|---|---|---|---|
| Knowledge | MMLU-Pro | 70.4 | 81.2 |
| Knowledge | MMLU-Redux | 83.7 | - |
| Reasoning | GPQA | 55.9 | 68.4 |
| Reasoning | AIME 25 | 65.6 | 70.9 |
Build with TNSA models
Explore model families, snapshots, and developer tools for production AI systems.