Models
OpenTyphoon.ai offers several models optimized for Thai language understanding and generation. Each model has different capabilities, performance characteristics, and rate limits.
Available Models
| Model ID | Size | Description | Context Window | Rate Limits | Release Date |
|---|---|---|---|---|---|
| typhoon-v2-8b-instruct | 8B | Improved model for general Thai language tasks | 8K tokens | 5 req/s, 50 req/m | 2024-12-19 |
| typhoon-v2-70b-instruct | 70B | Our most powerful model with advanced Thai language capabilities | 8K tokens | 5 req/s, 50 req/m | 2024-12-19 |
Model Details
typhoon-v2-70b-instruct
Our flagship model, typhoon-v2-70b-instruct, is designed for advanced Thai language understanding and generation. It excels at:
- Complex Thai language understanding and generation
- Following detailed instructions in both Thai and English
- Maintaining context over longer conversations
- Code understanding and generation
- Creative writing and content generation in Thai
Best For: Applications requiring the highest quality Thai language understanding and generation, including customer support, content creation, and complex question answering.
typhoon-v2-8b-instruct
A smaller but still powerful model, typhoon-v2-8b-instruct offers good performance for general Thai language tasks with lower latency and cost:
- Good Thai language understanding and generation
- Following instructions in both Thai and English
- Basic coding tasks
- Content generation and summarization
Best For: Applications requiring good Thai language capabilities with lower latency and higher throughput, such as real-time assistants and high-volume applications.
Choosing the Right Model
Consider these factors when choosing a model:
- Task Complexity: More complex tasks generally benefit from larger models
- Response Speed: Smaller models generally have lower latency
- Rate Limits: Consider your application’s volume requirements
- Quality Requirements: Higher quality generally requires larger models
For most applications requiring high-quality Thai language understanding and generation, we recommend using typhoon-v2-70b-instruct. If you need higher throughput or have simpler requirements, consider using typhoon-v2-8b-instruct.
Research and Development
Our models are built on extensive research in Thai language processing. You can learn more about the technical details in our research papers:
Future Models
We’re continuously working on improving our models and will release new versions as they become available. Stay updated by following our blog or joining our Discord community.