Back

Typhoon2 70B Instruct

Llama3
Input: text
Output: text
Released: Mar 28, 2025Updated: May 16, 2025

Llama3.1-Typhoon2-70B-Instruct is a Thai-English instruction-tuned language model with 70 billion parameters, built on Llama 3.1. It demonstrates strong performance across general instruction-following, math, coding, and tool-use tasks, with state-of-the-art results in Thai-specific benchmarks such as IFEval, MT-Bench, and Thai-English code-switching.

The model excels in bilingual reasoning and function-calling scenarios, offering high accuracy across diverse domains. Comparative evaluations show consistent improvements over prior Thai LLMs and other Llama-based baselines. Full 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-$0.88/M$0.88/M33.9 t/s929 ms
Standard Pricing
Input Tokens
$0.00000088

per 1K tokens

Output Tokens
$0.00000088

per 1K tokens

Do Work. With AI.