Back

Typhoon2 8B Instruct

Llama3
Input: text
Output: text
Released: Mar 28, 2025Updated: Mar 28, 2025

Llama3.1-Typhoon2-8B-Instruct is a Thai-English instruction-tuned model with 8 billion parameters, built on Llama 3.1. It significantly improves over its base model in Thai reasoning, instruction-following, and function-calling tasks, while maintaining competitive English performance. The model is optimized for bilingual interaction and performs well on Thai-English code-switching, MT-Bench, IFEval, and tool-use benchmarks.

Despite its smaller size, it demonstrates strong generalization across math, coding, and multilingual benchmarks, outperforming comparable 8B models across most Thai-specific tasks. Full benchmark results and methodology are available in the technical report.

8,192 Token Context

Process and analyze large documents and conversations.

Advanced Coding

Improved capabilities in front-end development and full-stack updates.

Agentic Workflows

Autonomously navigate multi-step processes with improved reliability.

Available On

ProviderModel IDContextMax OutputInput CostOutput CostThroughputLatency
Togethertogether8K-$0.18/M$0.18/M73.3 t/s270 ms
Standard Pricing
Input Tokens
$0.00000018

per 1K tokens

Output Tokens
$0.00000018

per 1K tokens

Do Work. With AI.