How do you build Turkish AI apps with Plugsky?

Key facts

Turkish text	Latin script, left-to-right; dotted and dotless i affect casing
Tokenisation	Agglutinated suffix chains split into many subwords — measure with the Plugsky token calculator
Register	siz and sen change verb forms throughout — keep one per surface
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

• Turkish needs only a base_url change on the standard endpoint.
• Suffix chains fragment heavily — measure tokens on real text.
• Apply Turkish-aware casing (İ/i and I/ı) in search.
• Pin siz or sen formality per surface.
• plugsky-embed-multilingual covers Turkish 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 Turkish 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: apply Turkish case-folding rules and standardise loanword spelling.
5. For RAG, embed with plugsky-embed-multilingual and test cross-language queries alongside Turkish-only queries.
6. Score candidate models on a Turkish gold set with native-speaker review, then cut production traffic over.

Try it yourself

Open the token calculator →

How Plugsky handles Turkish text

Turkish uses the Latin alphabet and reads left to right, with dotted and dotless i (İ/i and I/ı) that change case differently from English.

Formal and informal address (siz versus sen) and the spelling of modern loanwords are the main register choices.

Evaluate on formal and informal Turkish samples; check suffix chains, vowel harmony and correct dotted or dotless i usage.

Tokenisation and cost in Turkish

Turkish agglutination stacks suffixes into long words such as evlerinizdekiler that tokenisers split heavily, so token counts run high relative to word counts, and case folding with Turkish i rules matters for search.

• Apply Turkish-aware case folding (İ to i, I to ı) in search code.
• Keep suffix chains intact in display text.
• Test formal and informal address separately.
• Count tokens on real user text with long verbs and suffixes.

Turkish retrieval and RAG

Turkish retrieval improves with stemming and Turkish-aware casing; keep original forms for display and embeddings, and add stems for keyword search.

• Use plugsky-embed-multilingual for Turkish and English corpora.
• Apply Turkish case-folding rules in keyword search.
• Consider stemming for agglutinated forms.
• Evaluate formal and informal query sets.

Code example: a Turkish request

Point your existing OpenAI client at https://api.plugsky.com/v1 and pass Turkish 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": "Bu sözleşmeyi Türkçe olarak üç maddede özetle."}])

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

Honest comparison

Capability	Plugsky	Turkish workflow today	Building in-house
API compatibility	OpenAI-compatible — change base_url and model name	Varies by provider and SDK	Full rewrite
Turkish text handling	Turkish-aware casing with suffix-aware retrieval	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 Turkish text?

Yes. The API accepts UTF-8 Turkish 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 Turkish?

Turkish agglutination stacks suffixes into long words such as evlerinizdekiler that tokenisers split heavily, so token counts run high relative to word counts, and case folding with Turkish i rules matters for search. Use the token calculator at /tools/llm-token-calculator before sizing context windows or chunk lengths.

Siz or sen?

Use siz for business and formal products, sen for consumer apps. Keep the choice consistent across prompts and examples.

Why does Turkish casing break search?

The dotted and dotless i follow Turkish rules: İ lowercases to i and I lowercases to ı. Standard case folding gets this wrong, so apply Turkish rules.

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.