Happy Horse 1.0 is now on ModelsLab

Try Now
Skip to main content
Available now on ModelsLab · Language Model

Typhoon 2 70B InstructMaster Thai Instructions

Try Typhoon 2 70B InstructAPI Documentation

Deploy Typhoon Precision

Bilingual Power

Thai-English Instruct

Handles ThaiExam at 63%, ONET at 65% with Llama 3.1 base.

Extended Context

128K Token Window

Processes complex documents via Typhoon 2 70B Instruct model.

Function Calling

Advanced Tool Use

Leads IFEval-TH, MT-Bench for Typhoon 2 70B Instruct API tasks.

Examples

See what Typhoon 2 70B Instruct can create

Copy any prompt below and try it yourself in the playground.

Thai Summary

“Summarize this Thai news article on economic policy in 200 words, highlighting key impacts on businesses. Article: [insert Thai text]. Output in Thai.”

Bilingual Q&A

“Answer in Thai and English: What are the main causes of climate change? Provide three examples with data from recent reports.”

Code Generation

“Write Python code to analyze Thai text sentiment using transformers library. Include function calling for API integration.”

Legal Analysis

“Analyze this Thai contract excerpt for compliance risks. Suggest edits in bullet points, Thai only.”

For Developers

A few lines of code.
Instruct Typhoon. One Call.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per token, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/llm/chat/completions",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "",
  "model_id": ""
}
)
print(response.json())

FAQ

Common questions about Typhoon 2 70B Instruct

Read the docs

Instruction-tuned 70B model on Llama 3.1 for Thai-English tasks. Excels in benchmarks like IFEval-TH and MT-Bench. Supports 128K context.

Integrate via LLM endpoint with standard chat completions. Pass Thai or English prompts directly. Handles function calling natively.

Tops Thai benchmarks: ThaiExam 63.39%, ONET 65.43%. Strong in math, coding, bilingual reasoning over prior LLMs.

Outperforms Typhoon1.5x in A-Level, TGAT scores. Use for Thai-specific apps needing instruction following.

Supports 128,000 tokens for long documents. Ideal for legal analysis, multi-turn Thai conversations.

Apache 2.0 or Llama 3.1 Community License. Deploy freely via typhoon 2 70b instruct API.

Ready to create?

Start generating with Typhoon 2 70B Instruct on ModelsLab.

Try Typhoon 2 70B InstructAPI Documentation