OpenAI

llm

GPT-4o

GPT-4o

GPT-4o

OpenAI's flagship multimodal model. Best for complex reasoning and high-quality generation where GPT-4o-mini isn't enough.

OpenAI's flagship multimodal model. Best for complex reasoning and high-quality generation where GPT-4o-mini isn't enough.

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","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","messages":[{"role":"user","content":"Hello"}]}'

Context window

128K

128K

Max output

16K

16K

Credits

12.375 credits / 1K input tokens, 74.25 credits / 1K output tokens

USD equivalent

$2.50 / $10.00 per 1M tokens (input/output)

MODEL NOTES

GPT-4o is OpenAI's flagship multimodal model — the one to reach for when GPT-4o mini's answers feel shallow or miss nuance. It's noticeably better at following complex instructions, handling ambiguous requests, and producing polished, professional writing.

The cost difference versus GPT-4o mini is real (roughly 16x on Apiarium's credit pricing), so it's worth testing whether your specific use case actually needs it. A good pattern: prototype with GPT-4o mini, and only switch a specific endpoint or feature to GPT-4o once you've confirmed the quality gap matters for that particular task.

Available on Apiarium's Pro and Studio plans.

‹ GPT-4o mini

Claude Haiku 4.5 ›