Aipass API

AI Pass API — Complete Skill

All AI features via $AIPASS_API_KEY. No browser, no SDK, no OAuth needed.

Wrong skill? If you're shipping a product where other users sign in (web, mobile, desktop, CLI, ChatGPT App, or multi-tenant service), stop and use aipass-integration instead. That flow uses per-user OAuth authorization and bills each user's AI Pass wallet. This skill is for personal, internal, or developer-funded use only.

Auth

All endpoints: Authorization: Bearer $AIPASS_API_KEY Get your key: https://aipass.one/panel/developer.html → API Keys

Base URL

https://aipass.one/v1

The shared /v1 resource API selects API-key authentication from the bearer token. Existing /apikey/v1 URLs remain supported as compatibility aliases.

List Available Models

The default response is the OpenAI-compatible { "object": "list", "data": [...] } envelope. Filter by catalog metadata instead of provider-name patterns:

curl -sS "https://aipass.one/v1/models?type=image&method=image_generation" \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  | jq -r '.data[].id'

The explicit compatibility query ?detailed=false returns the historical string array.

Recommended Stable IDs

Confirm each ID through runtime discovery before use.

Text Generation (Chat Completions)

Image Generation

Image Editing

Text-to-Speech

Text Embeddings

Audio (Speech-to-Text + Audio Understanding)

Video Generation

1. Text Generation (Chat Completions)

Endpoint: POST /v1/chat/completions

curl -s -X POST https://aipass.one/v1/chat/completions \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-mini",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Your prompt here"}
    ]
  }'

Response: response.choices[0].message.content

Python

import requests, os
AIPASS_API_KEY = os.environ["AIPASS_API_KEY"]

def chat(prompt, model="gpt-5-mini", system="You are a helpful assistant."):
    r = requests.post("https://aipass.one/v1/chat/completions",
        headers={"Authorization": f"Bearer {AIPASS_API_KEY}", "Content-Type": "application/json"},
        json={"model": model, "messages": [
            {"role": "system", "content": system},
            {"role": "user", "content": prompt}
        ]})
    return r.json()["choices"][0]["message"]["content"]

2. Image Generation

Endpoint: POST /v1/images/generations

curl -s -X POST https://aipass.one/v1/images/generations \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-pro-v1.1",
    "prompt": "A cute monster with big eyes and small horns, digital art",
    "size": "1024x1024",
    "n": 1
  }'

Response: response.data[0].url (image URL) or response.data[0].b64_json (base64)

Python

def generate_image(prompt, model="flux-pro-v1.1", size="1024x1024"):
    r = requests.post("https://aipass.one/v1/images/generations",
        headers={"Authorization": f"Bearer {AIPASS_API_KEY}", "Content-Type": "application/json"},
        json={"model": model, "prompt": prompt, "size": size, "n": 1})
    return r.json()["data"][0]["url"]

Download image

URL=$(curl -s -X POST https://aipass.one/v1/images/generations \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"flux-pro-v1.1","prompt":"your prompt","size":"1024x1024","n":1}' \
  | python3 -c "import json,sys; print(json.load(sys.stdin)['data'][0]['url'])")
curl -s "$URL" -o output.png

3. Image Editing

Endpoint: POST /v1/chat/completions (routes through chat completions for Gemini image models)

⚠️ Note: The /v1/images/edits endpoint has a known bug. Use chat completions with base64 image instead.

import base64

def edit_image(image_path, prompt, model="gemini-3-pro-image-preview"):
    with open(image_path, "rb") as f:
        b64 = base64.b64encode(f.read()).decode()
    
    ext = image_path.rsplit(".", 1)[-1].lower()
    mime = {"png": "image/png", "jpg": "image/jpeg", "jpeg": "image/jpeg", "webp": "image/webp"}.get(ext, "image/png")
    
    r = requests.post("https://aipass.one/v1/chat/completions",
        headers={"Authorization": f"Bearer {AIPASS_API_KEY}", "Content-Type": "application/json"},
        json={
            "model": model,
            "messages": [{
                "role": "user",
                "content": [
                    {"type": "text", "text": prompt},
                    {"type": "image_url", "image_url": {"url": f"data:{mime};base64,{b64}"}}
                ]
            }]
        })
    return r.json()["choices"][0]["message"]["content"]

Bash

B64=$(base64 -w0 input.png)
curl -s -X POST https://aipass.one/v1/chat/completions \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-image-preview",
    "messages": [{"role": "user", "content": [
      {"type": "text", "text": "Remove the background"},
      {"type": "image_url", "image_url": {"url": "data:image/png;base64,'$B64'"}}
    ]}]
  }'

4. Text-to-Speech

Endpoint: POST /v1/audio/speech

Voices: alloy, echo, fable, onyx, nova, shimmer

curl -s -X POST https://aipass.one/v1/audio/speech \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello, this is AI Pass speaking!",
    "voice": "nova"
  }' --output speech.mp3

Python

def text_to_speech(text, voice="nova", model="tts-1", output="speech.mp3"):
    r = requests.post("https://aipass.one/v1/audio/speech",
        headers={"Authorization": f"Bearer {AIPASS_API_KEY}", "Content-Type": "application/json"},
        json={"model": model, "input": text, "voice": voice})
    with open(output, "wb") as f:
        f.write(r.content)
    return output

5. Audio Transcription (Speech-to-Text)

Endpoint: POST /v1/audio/transcriptions

Formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg

curl -s -X POST https://aipass.one/v1/audio/transcriptions \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  -F "file=@audio.mp3" \
  -F "model=whisper-1" \
  -F "language=en"

Response: response.text

Python

def transcribe(file_path, language="en"):
    with open(file_path, "rb") as f:
        r = requests.post("https://aipass.one/v1/audio/transcriptions",
            headers={"Authorization": f"Bearer {AIPASS_API_KEY}"},
            files={"file": f},
            data={"model": "whisper-1", "language": language})
    return r.json()["text"]

6. Video Generation (Async)

Endpoint: POST /v1/videos

Video generation is async — start, poll, download.

import time

def generate_video(prompt, model="veo-3.1-fast-generate-preview", seconds=5):
    # Start
    r = requests.post("https://aipass.one/v1/videos",
        headers={"Authorization": f"Bearer {AIPASS_API_KEY}", "Content-Type": "application/json"},
        json={"model": model, "prompt": prompt, "seconds": seconds})
    video_id = r.json()["videoId"]
    
    # Poll
    while True:
        status = requests.get(f"https://aipass.one/v1/videos/{video_id}/status",
            headers={"Authorization": f"Bearer {AIPASS_API_KEY}"}).json()
        if status["status"] == "completed":
            return status["downloadUrl"]
        elif status["status"] == "failed":
            raise Exception(f"Failed: {status}")
        time.sleep(5)

Bash

# Start video generation
VIDEO_ID=$(curl -s -X POST https://aipass.one/v1/videos \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"veo-3.1-fast-generate-preview","prompt":"A monster dancing in the rain","seconds":5}' \
  | python3 -c "import json,sys; print(json.load(sys.stdin)['videoId'])")

# Poll status
curl -s "https://aipass.one/v1/videos/$VIDEO_ID/status" \
  -H "Authorization: Bearer $AIPASS_API_KEY"

Quick Reference

7. Text Embeddings

Endpoint: POST /v1/embeddings

curl -s -X POST https://aipass.one/v1/embeddings \
  -H "Authorization: Bearer $AIPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "Your text to embed"
  }'

Response: response.data[0].embedding (array of floats)

Python

def embed(text, model="text-embedding-3-small"):
    r = requests.post("https://aipass.one/v1/embeddings",
        headers={"Authorization": f"Bearer {AIPASS_API_KEY}", "Content-Type": "application/json"},
        json={"model": model, "input": text})
    return r.json()["data"][0]["embedding"]

# Batch embedding
def embed_batch(texts, model="text-embedding-3-small"):
    r = requests.post("https://aipass.one/v1/embeddings",
        headers={"Authorization": f"Bearer {AIPASS_API_KEY}", "Content-Type": "application/json"},
        json={"model": model, "input": texts})
    return [d["embedding"] for d in r.json()["data"]]

Cost Tips

• gpt-5-nano for simple text (cheapest)
• gemini-2.5-flash-lite for cheap text with good quality
• flux-pro-v1.1 for standard images (~$0.05)
• whisper-1 for audio — very cheap
• tts-1 cheaper than tts-1-hd
• gpt-image-1-mini cheaper than gpt-image-1

Building Apps with AI Pass SDK

If building web apps (not server-side), use the JS SDK instead:

<script src="https://aipass.one/aipass-sdk.js"></script>
<script>
AiPass.initialize({ clientId: 'YOUR_CLIENT_ID', requireLogin: true, darkMode: true });
</script>

Get your Client ID: https://aipass.one/panel/developer.html → OAuth2 Clients

SDK methods mirror the API: AiPass.generateCompletion(), AiPass.generateImage(), AiPass.editImage(), AiPass.generateSpeech(), AiPass.transcribeAudio(), AiPass.generateVideo()

Developers earn 50% commission on every API call their users make.

Full SDK docs: https://aipass.one/docs/sdk/reference.html