Shisa LLM
Shisa LLM is a family of large language models tuned for Japanese, fluent in English, and served behind an OpenAI-compatible API. If you already use the OpenAI SDKs, you can point them at Shisa by changing two lines — the base URL and the model name.
POST https://api.shisa.ai/openai/v1/chat/completions
Why Shisa LLM
- Japanese expertise — trained and evaluated on Japanese data, with strong cultural and linguistic nuance rather than translated English behaviour.
- Bilingual proficiency — high quality across Japanese and English, and reliable switching between them in a single conversation.
- OpenAI-compatible — works with
openai-python,openai-node, and any client that speaks the Chat Completions API. - Streaming — token-by-token Server-Sent Events for responsive UIs.
- Japan-hosted — inference runs in Japan for data-residency-sensitive workloads.
- Reduced language leakage — markedly fewer stray non-Japanese tokens than general-purpose models (up to 47.8× reduction versus the base model).
Benchmarks
| Metric | Score | Model |
|---|---|---|
| Japanese MT-Bench | 9.26 | Shisa V2.1 Pro |
| Japanese average | 73.1% | Shisa V2.1 Pro |
| Japanese average | 80.5% | Shisa V2 405B |
| Language-leakage reduction | 47.8× | vs. base model |
Read the technical write-ups for Shisa V2.1 and Shisa V2 405B.
Next steps
- Quickstart — make your first request with curl, Python, or Node.
- Models — choose between Flash, Pro, and the 405B flagship.
- Chat completions reference — request and response schema.
- Pricing — how LLM usage is billed.