Key facts
| Italian text | Latin script with accents and elisions such as l'utente handled as-is |
| Register | Formal Lei and informal tu change verb forms — keep one per surface |
| Tokenisation | Apostrophised and accented forms can split into subwords — measure with the Plugsky token calculator |
| API compatibility | OpenAI-compatible POST https://api.plugsky.com/v1/chat/completions — chat, streaming, JSON mode and function calling |
| Models | 30+ models behind one endpoint, from free tiers to frontier reasoning |
| Free tier | Free plan with plugsky-micro and plugsky-lite, no card required |
| Deployment | Plugsky cloud, your VPC, on-prem and air-gapped options |
| Product status | Chat, streaming, JSON mode, function calling, embeddings, RAG and agents live; audio, images, batch and fine-tuning coming soon |
TL;DR
- Italian needs only a base_url change — no separate endpoint.
- Accents and elisions are the main tokenisation risk.
- Pin formal Lei or informal tu per surface.
- Keep accents in embeddings; normalise search keys.
- plugsky-embed-multilingual handles Italian and English RAG.
How it works, step by step
- Create a Plugsky API key on the free plan (no card) and set base_url to https://api.plugsky.com/v1.
- Send a small set of real Italian prompts to /v1/chat/completions and compare output across two or three models.
- Count tokens for those prompts with the Plugsky token calculator and set chunk sizes that fit your model context.
- Normalise text before indexing or prompting: NFC-normalise accents and preserve apostrophes.
- For RAG, embed with plugsky-embed-multilingual and test cross-language queries alongside Italian-only queries.
- Score candidate models on a Italian gold set with native-speaker review, then cut production traffic over.
Try it yourself
Open the OpenAI cost calculator →
How Plugsky handles Italian text
Italian uses the Latin alphabet with accents and apostrophes such as l'utente and un'ora, and reads left to right.
Formal Lei and informal tu change verb forms and pronouns, and regional vocabulary varies across Italy.
Evaluate on a small Italian gold set: check accented vowels, elisions and Lei/tu consistency, which automated metrics tend to miss.
Tokenisation and cost in Italian
Italian tracks English closely on token cost, but apostrophised forms and accented final vowels can split into subwords, and Italian phrasing often needs slightly more words for the same meaning.
- Keep apostrophes and accents in text; normalise only search keys.
- Pin Lei or tu per product surface.
- Test regional vocabulary such as food and retail terms in evals.
- Measure tokens on your actual marketing or legal copy.
Italian retrieval and RAG
Italian documents retrieve well alongside English queries in a shared multilingual collection; keep accents in embedding text and normalise for keyword search.
- Use plugsky-embed-multilingual for Italian and English corpora.
- NFC-normalise accented characters.
- Keep elisions from breaking chunk boundaries.
- Evaluate formal and regional vocabulary variants.
Code example: a Italian request
Point your existing OpenAI client at https://api.plugsky.com/v1 and pass Italian text in the content field — no language flag and no separate endpoint. Streaming, JSON mode and function calling keep the same request shapes.
client = OpenAI(base_url="https://api.plugsky.com/v1", api_key=os.environ["PLUGSKY_API_KEY"])
client.chat.completions.create(model="plugsky-pro", messages=[{"role": "user", "content": "Riassumi questo contratto in tre punti, in italiano."}])
Start on the free plan with plugsky-micro and plugsky-lite, then compare paid models on a Italian gold set before cutover. See the docs for request details.
For production, log the model name and your normalisation settings with each request, and re-run the Italian gold set whenever either changes — language quality regressions usually come from prompt or preprocessing drift, not from the model alone.
Honest comparison
| Capability | Plugsky | Italian workflow today | Building in-house |
|---|---|---|---|
| API compatibility | OpenAI-compatible — change base_url and model name | Varies by provider and SDK | Full rewrite |
| Italian text handling | Accent-preserving text with one Lei/tu register | Depends on provider tokeniser and prompt hygiene | You build normalisation, segmentation and evals |
| Token budget | Fixed tokeniser per model; measure with the Plugsky token calculator and chunk to fit | Varies by provider and model | You host and tune each tokeniser |
| Multilingual retrieval | plugsky-embed-multilingual available for cross-language RAG | Often needs a separate embedding vendor | You serve and maintain embeddings |
| Sovereignty | Cloud, VPC, on-prem and air-gapped with residency options | Usually US/EU public endpoints | You own the full stack |
Frequently asked questions
Can Plugsky handle Italian text?
Yes. The API accepts UTF-8 Italian input on the OpenAI-compatible chat endpoint; output quality depends on the model, so compare two or three on your own prompts before choosing.
How do I estimate token usage for Italian?
Italian tracks English closely on token cost, but apostrophised forms and accented final vowels can split into subwords, and Italian phrasing often needs slightly more words for the same meaning. Use the token calculator at /tools/llm-token-calculator before sizing context windows or chunk lengths.
Lei or tu for Italian products?
Lei for formal and enterprise contexts, tu for consumer apps. Decide once and keep verbs and pronouns consistent.
Do apostrophes break tokenisation?
Elisions such as l'utente can split into subwords. Keep apostrophes in display text and test a sample of real sentences for token counts.
Is there a multilingual embedding model?
Yes — plugsky-embed-multilingual is part of the 30+ model catalogue and is built for cross-language retrieval. Keep one embedding model per vector collection.
Can I keep data in my region?
Plugsky supports cloud, VPC, on-prem and air-gapped deployment with data-residency options; confirm your requirements with the docs and the enterprise team.
How do I migrate an existing app?
Change base_url to https://api.plugsky.com/v1 and map the model name. Streaming, JSON mode, function calling and embeddings keep the same request shapes.
Is there a free plan?
Yes — the free plan includes two free models, plugsky-micro and plugsky-lite, with no card. A 14-day full-access trial unlocks the paid catalogue.