OpenAI-compatible

Quickstart

One ck- key works with any OpenAI-compatible client. Point the base URL here, pick a model, done.

Base URLhttps://conduit-api.aurixel.ai/v1

1Sign up

Create an account in seconds — free starter credit included.

2Create a key

Grab a ck-… key on the API Keys page.

3Call any model

Use the snippet below in code or your editor.

Call the API

Replace ck-YOUR_KEY with your key. Any OpenAI SDK works.

curl https://conduit-api.aurixel.ai/v1/chat/completions \
  -H "Authorization: Bearer ck-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Which endpoint?

Most models use chat completions — image and audio use their own.

Chat / textPOST /v1/chat/completionsall text models

Image — generatePOST /v1/images/generationsgpt-image-2 · gemini-3-pro-image-preview → data[0].b64_json

Image — via chatPOST /v1/chat/completionsgemini-3.1-flash-image → message.images

Text-to-speechPOST /v1/audio/speechqwen-tts · qwen3-tts-vc

Speech-to-textPOST /v1/audio/transcriptionsdeepgram-nova-3 · speechmatics-*

Reasoning effort: model-high / -low / -xhigh suffix, or the reasoning_effort param (gpt-5.x / o3 / claude). Gemini uses -low / -agent variants.

Use it in your editor

Drop these into your favorite AI client.

Paste into ~/.codex/config.toml

model = "gpt-5.5"
model_provider = "aurixel"

[model_providers.aurixel]
name = "Aurixel"
base_url = "https://conduit-api.aurixel.ai/v1"
wire_api = "responses"
requires_openai_auth = false
experimental_bearer_token = "ck-YOUR_KEY"

Tip — after signing in, Integrations generates a key and fills these in with one click.

Ready to build?

Free OAuth quota to get you started.