OpenAI

llm

GPT-4o mini

GPT-4o mini

GPT-4o mini

The fastest, most affordable way to add GPT-4o-class text generation to your product. Included free on every Apiarium plan.

The fastest, most affordable way to add GPT-4o-class text generation to your product. Included free on every Apiarium plan.

All models

chat, vision

REQUEST

llm

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"}]}'

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"}]}'

Context window

128K

128K

Max output

16K

16K

Credits

0.75 credits / 1K input tokens, 4.5 credits / 1K output tokens

USD equivalent

$0.15 / $0.60 per 1M tokens (input/output)

MODEL NOTES

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.

GPT-4o ›