How do you build Spanish AI apps with Plugsky?

Key facts

Spanish text	Latin script with ñ, accents and inverted punctuation ¿ ¡
Locale variants	Spain and Latin America differ in vocabulary and address forms
Tokenisation	Long verb forms and accented text can split — 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

• Spanish runs on the standard OpenAI-compatible endpoint.
• Keep accents and the ¿ ¡ marks — they are not optional.
• Pin tú, vos or usted per market.
• Track es-ES and LatAm vocabulary as separate eval slices.
• plugsky-embed-multilingual covers Spanish and English retrieval.

How it works, step by step

1. Create a Plugsky API key on the free plan (no card) and set base_url to https://api.plugsky.com/v1.
2. Send a small set of real Spanish prompts to /v1/chat/completions and compare output across two or three models.
3. Count tokens for those prompts with the Plugsky token calculator and set chunk sizes that fit your model context.
4. Normalise text before indexing or prompting: NFC-normalise accents and pick one regional vocabulary.
5. For RAG, embed with plugsky-embed-multilingual and test cross-language queries alongside Spanish-only queries.
6. Score candidate models on a Spanish gold set with native-speaker review, then cut production traffic over.

Try it yourself

Open the OpenAI cost calculator →

How Plugsky handles Spanish text

Spanish uses the Latin alphabet with ñ and accents, and opens questions and exclamations with inverted marks (¿ and ¡).

Spain and Latin America differ in vocabulary, and address forms tú, vos and usted vary by country and formality.

Evaluate on Spain and Latin American samples; check accent marks, agreement and address forms, which automated metrics tend to miss.

Tokenisation and cost in Spanish

Spanish is close to English on token cost; accented vowels and inverted punctuation are handled reliably by modern tokenisers, but long verb forms and regional vocabulary affect counts modestly.

• Keep inverted punctuation and accents — they carry meaning.
• Pick one address form per surface and country.
• Maintain a Spain versus Latin America vocabulary glossary.
• Measure tokens on your real content, not translated samples.

Spanish retrieval and RAG

One multilingual collection can serve Spanish documents and English queries, but evaluate Spain and Latin American vocabulary variants separately for retrieval precision.

• Use plugsky-embed-multilingual for Spanish and English corpora.
• NFC-normalise accents before embedding.
• Track es-ES and es-419 queries separately.
• Add regional synonyms to keyword search.

Code example: a Spanish request

Point your existing OpenAI client at https://api.plugsky.com/v1 and pass Spanish 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": "Resume este contrato en tres puntos, en español."}])

Start on the free plan with plugsky-micro and plugsky-lite, then compare paid models on a Spanish 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 Spanish gold set whenever either changes — language quality regressions usually come from prompt or preprocessing drift, not from the model alone.

Honest comparison

Capability	Plugsky	Spanish workflow today	Building in-house
API compatibility	OpenAI-compatible — change base_url and model name	Varies by provider and SDK	Full rewrite
Spanish text handling	One regional vocabulary with ¿ ¡ and accents preserved	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 Spanish text?

Yes. The API accepts UTF-8 Spanish 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 Spanish?

Spanish is close to English on token cost; accented vowels and inverted punctuation are handled reliably by modern tokenisers, but long verb forms and regional vocabulary affect counts modestly. Use the token calculator at /tools/llm-token-calculator before sizing context windows or chunk lengths.

Which Spanish variant should I target?

Choose Spain or Latin America per market and keep vocabulary consistent; neutral es-419 works for multi-country launches but reads flat in local markets.

Tú, vos or usted?

Decide per country and product surface. Usted for formal services, tú for most consumer apps, vos for Argentina, Uruguay and parts of Central America.

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.