One line to switch, same request shape
The Yiğido endpoint is OpenAI-compatible. Point your existing SDK at it, swap the model name, keep everything else.
curl https://api.yigido.dev/v1/chat/completions \
-H "Authorization: Bearer $YIGIDO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "yigido-1.0-max",
"stream": true,
"messages": [
{ "role": "user", "content": "Merhaba, kendini tanıt." }
]
}'Endpoints
/v1/chat/completions Chat completions. Streaming (SSE) or single JSON response. /v1/embeddings 1280-dim sentence embeddings, Turkish-optimised. /v1/models Lists the models this key can reach. /v1/healthz Service liveness probe. Streaming
Send "stream": true and you get text/event-stream frames in the OpenAI delta format, terminated by data: [DONE]. The chat window on this site renders tokens as they arrive — that is the whole front-end.
Self-hosting the endpoint
Weights ship with a vLLM launch script, so you can run the same endpoint on your own hardware. The 1.0 Mini checkpoint fits on a single 24 GB card.
Choose your best plan
Same model, three levels of commitment — from a free chat window to your own cluster.
Open
Chat with Yiğido 1.0 Mini and read the eval harness. No card, no key queue.
- Yiğido 1.0 Mini · 420 tok/s
- 2,000 requests / day
- 32K context
- Community support
Developer
Yiğido 1.0 Max with streaming, tool calls and a real rate limit.
- Yiğido 1.0 Max · 128K context
- 1M tokens / month included
- Streaming + tool calling
- Eval harness access
- Email support · 24 hours
Scale
Self-host the open weights or run dedicated capacity in the TR/EU region.
- Dedicated H100 capacity
- Custom Turkish-domain fine-tune
- Data residency: TR / EU
- 99.9% SLA + engineer support