Key facts
| Portuguese text | Latin script with accents, cedilla and nasal vowels — handle as UTF-8 |
| Locale variants | pt-BR and pt-PT differ in vocabulary and clitic placement |
| Tokenisation | Accented and hyphenated 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
- Portuguese uses the same API — one base_url change.
- NFC-normalise accents and cedillas before indexing.
- Pin pt-BR or pt-PT vocabulary per product.
- Hyphenated clitics can inflate token counts — measure.
- plugsky-embed-multilingual covers Portuguese and English retrieval.
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 Portuguese 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 cedillas.
- For RAG, embed with plugsky-embed-multilingual and test cross-language queries alongside Portuguese-only queries.
- Score candidate models on a Portuguese gold set with native-speaker review, then cut production traffic over.
Original data
Try it yourself
Open the OpenAI cost calculator →
How Plugsky handles Portuguese text
Portuguese uses the Latin alphabet with accents, cedilla (ç) and nasal vowels (ã, õ), and reads left to right.
Brazilian and European Portuguese differ in vocabulary, pronoun placement and gerund usage, and formal o senhor or você versus informal você or tu varies by region.
Evaluate on pt-BR and pt-PT samples; check accents, clitic placement and vocabulary consistency, which differ enough to matter for local readers.
Tokenisation and cost in Portuguese
Portuguese is close to English in token efficiency; accented characters and clitic pronouns such as dar-lhe can split into subwords, especially in hyphenated forms.
- Normalise to NFC so accents stay composed.
- Pick pt-BR or pt-PT vocabulary and keep it consistent.
- Keep hyphenated clitics intact in display text.
- Measure tokens on legal or formal copy where clitics concentrate.
Portuguese retrieval and RAG
Serve pt-BR and pt-PT from one collection but track separate eval slices, since vocabulary differences affect retrieval precision.
- Use plugsky-embed-multilingual for Portuguese and English retrieval.
- NFC-normalise accents before embedding.
- Track pt-BR and pt-PT queries separately.
- Add synonyms for cross-variant vocabulary.
Code example: a Portuguese request
Point your existing OpenAI client at https://api.plugsky.com/v1 and pass Portuguese 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": "Resuma este contrato em três pontos, em português."}])
Start on the free plan with plugsky-micro and plugsky-lite, then compare paid models on a Portuguese 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 Portuguese gold set whenever either changes — language quality regressions usually come from prompt or preprocessing drift, not from the model alone.
Honest comparison
| Capability | Plugsky | Portuguese workflow today | Building in-house |
|---|---|---|---|
| API compatibility | OpenAI-compatible — change base_url and model name | Varies by provider and SDK | Full rewrite |
| Portuguese text handling | One variant's vocabulary with NFC-normalised accents | 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 Portuguese text?
Yes. The API accepts UTF-8 Portuguese 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 Portuguese?
Portuguese is close to English in token efficiency; accented characters and clitic pronouns such as dar-lhe can split into subwords, especially in hyphenated forms. Use the token calculator at /tools/llm-token-calculator before sizing context windows or chunk lengths.
Brazilian or European Portuguese?
Pick one variant per product and keep vocabulary consistent. pt-BR has the larger developer base, but pt-PT matters for Portugal-facing services.
Do accents affect retrieval?
NFC-normalise accents before embedding. Keep accents in display text — removing them changes meaning and reads as low quality.
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.