How do you build Tagalog AI apps with Plugsky?

Key facts

Tagalog text	Latin script with verb-focus affixes and reduplication
Code-switching	Taglish is the default digital register — define an explicit policy
Tokenisation	Affixed and reduplicated forms 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

• Tagalog needs only a base_url change — no special endpoint.
• Affixes and reduplication fragment tokens; measure real messages.
• Set a Taglish policy: how much English mixing is acceptable.
• One multilingual collection can serve Tagalog and English.
• Evaluate pure Tagalog and Taglish separately.

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 Tagalog 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: standardise product-term spelling and keep Taglish as written.
5. For RAG, embed with plugsky-embed-multilingual and test cross-language queries alongside Tagalog-only queries.
6. Score candidate models on a Tagalog gold set with native-speaker review, then cut production traffic over.

Try it yourself

Open the OpenAI-compatible API tester →

How Plugsky handles Tagalog text

Tagalog (Filipino) uses the Latin alphabet and reads left to right, with verb-focus affixes and reduplication carrying much of the grammar.

Formal Filipino and everyday Tagalog differ, and Taglish — Tagalog and English switching — is the default register in many digital products.

Evaluate on formal Filipino and Taglish samples with a native reviewer; check affix and focus consistency, which machine metrics cannot judge.

Tokenisation and cost in Tagalog

Affixes and reduplication such as mag-, -in, naka- and pa- split words into several tokens, and Taglish sentences mix two token profiles in one request, so counts vary widely by author.

• Decide how much Taglish is acceptable per surface and document it.
• Keep affixes and reduplication intact in display text.
• Maintain a glossary for recurring product terms in Filipino.
• Measure tokens on real user messages, where Taglish dominates.

Tagalog retrieval and RAG

Index documents in whichever language they are written and expect Taglish queries; one multilingual collection can serve both if you test mixed-language retrieval.

• Use plugsky-embed-multilingual for Tagalog and English corpora.
• Keep code-switched sentences intact when chunking.
• Add English and Tagalog synonyms for key terms.
• Evaluate pure Tagalog and Taglish queries separately.

Code example: a Tagalog request

Point your existing OpenAI client at https://api.plugsky.com/v1 and pass Tagalog 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": "Ibuod ang kontratang ito sa tatlong punto sa Tagalog."}])

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

Honest comparison

Capability	Plugsky	Tagalog workflow today	Building in-house
API compatibility	OpenAI-compatible — change base_url and model name	Varies by provider and SDK	Full rewrite
Tagalog text handling	Affix-aware retrieval with an explicit Taglish policy	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 Tagalog text?

Yes. The API accepts UTF-8 Tagalog 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 Tagalog?

Affixes and reduplication such as mag-, -in, naka- and pa- split words into several tokens, and Taglish sentences mix two token profiles in one request, so counts vary widely by author. Use the token calculator at /tools/llm-token-calculator before sizing context windows or chunk lengths.

How much Taglish should I allow?

Set an explicit policy. Pure Filipino suits formal and government content; Taglish is normal in consumer chat and should be accepted in prompts.

Does Filipino differ from Tagalog?

Filipino is the standardised national variety and includes more loaned terms. Tagalog dialects vary by province, so evaluate the register your users write.

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.