openai·chat
GPT-Realtime mini
openai/gpt-realtime-mini
At a glance
- · $0.60 input / $2.40 output per 1M tokens (provider list price, billed in credits)
- · OpenAI-compatible — model: "openai/gpt-realtime-mini" (provider: openai)
Detail page in progress
For GPT-Realtime mini we maintain specs sourced from provider documentation. A long-form breakdown of strengths, weaknesses, and use cases is in progress. The API already works — see the code snippet below.
How to call it
Drop-in OpenAI-compatible. Just swap the `model` string and you're using this model.
curl https://www.getmorecredits.com/v1/chat/completions \
-H "Authorization: Bearer $GMC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-realtime-mini",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Frequently asked questions
How much does GPT-Realtime mini cost?⌄
Input is $0.60 per million tokens; output is $2.40 per million tokens — provider list price. On getmorecredits.com you pay in credits, no subscription, no minimum spend.
Is GPT-Realtime mini OpenAI-compatible?⌄
Yes. On getmorecredits.com you call GPT-Realtime mini with the same request shape as OpenAI: POST /v1/chat/completions with "model": "openai/gpt-realtime-mini". Existing OpenAI SDKs (Python, Node, etc.) work by changing the base URL and API key.