GPT-4o mini
OpenAI
llm
chat, vision
0.75 credits / 1K input tokens, 4.5 credits / 1K output tokens
$0.15 / $0.60 per 1M tokens (input/output)
curl -X POST https://api.apiarium.dev/llm -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" -d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"Hello"}]}'
The fastest, most affordable way to add GPT-4o-class text generation to your product. Included free on every Apiarium plan.
GPT-4o mini is OpenAI's fastest and most affordable model, and it's what Apiarium uses as the default for the /llm endpoint. It handles everyday text generation well — drafting copy, summarizing content, answering questions, basic coding help — at a fraction of the cost of larger models.
If you're building a feature where response quality matters less than speed and cost (chat widgets, content drafts, quick classifications), start here. It's included free on every Apiarium plan, so there's no reason not to test your integration against it before deciding whether you need something more capable.
When it's not enough: complex multi-step reasoning, nuanced writing that needs a specific voice, or tasks requiring deep context. For those, Claude Sonnet or GPT-4o are worth the extra cost.