J JJAPI
δΈ­ζ–‡

OpenAI

Call the OpenAI API at a better rate β€” same SDK.

gpt-5.5, gpt-5.4-mini, gpt-5.3-codex, gpt-image-1, Whisper, embeddings β€” all callable through one JJAPI key with lifetime credit and no monthly minimum.

Get my API key β†’ Quickstart in 30 seconds β†’

Latest models as of 2026-07-06

See all models β†’
gpt-realtime-whisper specialized

OpenAI gpt-realtime-whisper. Auto-imported from /v1/models.
gpt-realtime-2 specialized

Low-latency voice + text streaming. For phone agents and live-audio interfaces.
gpt-realtime-translate specialized

OpenAI gpt-realtime-translate. Auto-imported from /v1/models.

Why use JJAPI for this API

No OpenAI account or phone verification

OpenAI requires phone verification and blocks several regions. JJAPI doesn't.

Drop-in OpenAI SDK

JJAPI's endpoint is byte-compatible with OpenAI's. Existing code needs only a base_url change.

Same payload, lower bill

Per-token rate matches OpenAI's published rate; your plan's credit bonus is pure savings.

Stream-perfect SSE

Server-sent events are passed through unchanged so streaming UIs work without modification.

example.py 
from openai import OpenAI

client = OpenAI(
    base_url="https://api.jjapi.net/v1",
    api_key="sk-jjapi-...",
)

r = client.chat.completions.create(
    model="gpt-realtime-whisper",  # current as of 2026-07-06
    messages=[{"role": "user", "content": "Hi"}],
)
print(r.choices[0].message.content)

Frequently asked

Do you support OpenAI tool calls and JSON mode?

Yes, fully. Both 'tools' and the legacy 'functions' parameter work, as does response_format=json_object and json_schema.

What about images / vision?

image_url and base64 inputs work on gpt-5.5 and gpt-5.4-mini. gpt-image-1 is callable via /v1/images/generations for generation.

Does Whisper / TTS work?

Yes: /v1/audio/transcriptions for Whisper, /v1/audio/speech for TTS voices.

Get my API key β†’