Media models

Create a workspace API key in the Overblast console and point your base URL at https://brain.deployd.network/ai/v1. Usage bills that workspace's AI tokens, at the prices shown here.

curl https://brain.deployd.network/ai/v1/images \
  -H "Authorization: Bearer ob_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3-pro-image",
    "prompt": "a red bicycle against a wet brick wall at night"
  }'

# → { "data": [ { "b64_json": "iVBORw0KGgo…" } ] }

A job, not a request: start it, poll it, download it. Polling is free — the tokens are charged to the render, and each render in flight needs $5.00 of AI tokens available.

Create a workspace API key in the Overblast console and point your base URL at https://brain.deployd.network/ai/v1. Usage bills that workspace's AI tokens, at the prices shown here.

# 1 · start the render. A render in flight needs $5.00 of AI tokens available.
curl https://brain.deployd.network/ai/v1/videos \
  -H "Authorization: Bearer ob_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "black-forest-labs/flux-video-edit",
    "prompt": "a paper plane crossing a sunlit kitchen, slow motion"
  }'

# → 202 { "id": "vid_123", "status": "queued" }

# 2 · poll until it says completed — the cost rides the job, not the poll
curl https://brain.deployd.network/ai/v1/videos/vid_123 \
  -H "Authorization: Bearer ob_live_YOUR_KEY"

# 3 · download it
curl https://brain.deployd.network/ai/v1/videos/vid_123/content \
  -H "Authorization: Bearer ob_live_YOUR_KEY" \
  -o out.mp4

Any model that takes audio transcribes here — 47 do, each at its own token prices on the Language tab.

Create a workspace API key in the Overblast console and point your base URL at https://brain.deployd.network/ai/v1. Usage bills that workspace's AI tokens, at the prices shown here.

curl https://brain.deployd.network/ai/v1/audio/transcriptions \
  -H "Authorization: Bearer ob_live_YOUR_KEY" \
  -F file=@audio.mp3 \
  -F model=google/gemini-2.5-flash

# → { "text": "…what was said…" }

A chat call with the audio modality: the reply carries a base64 clip beside the text. Voices and formats are the model's own.

Create a workspace API key in the Overblast console and point your base URL at https://brain.deployd.network/ai/v1. Usage bills that workspace's AI tokens, at the prices shown here.

curl https://brain.deployd.network/ai/v1/chat/completions \
  -H "Authorization: Bearer ob_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio",
    "modalities": ["text", "audio"],
    "audio": { "voice": "alloy", "format": "mp3" },
    "messages": [{ "role": "user", "content": "Read this aloud: your order is on its way." }]
  }'

# → base64 audio in choices[0].message.audio.data

Anything that speaks the OpenAI completions API runs every model here: one key, one base URL, one model id.

1. Pick your tool.
   00the app this catalog is built for ›_ Codex CLIterminal Py OpenAI SDKPython JS OpenAI SDKNode ⚙ Antigravity & othersany OpenAI-compatible tool
2. Get your key. Not needed for 00. For the rest: create a workspace API key in the Overblast console — usage bills that workspace's AI tokens, at the prices on this site.
3. Turn it on.

   Pick the model per agent — Settings → your agent → Model, and per tier, so different agents run different models.

   The media models are built in on your AI tokens: ask for a picture, a clip, a transcript or speech. No key, no provider account, no setup.

   Download free →

   Two variables and a model id.

   export OPENAI_BASE_URL="https://brain.deployd.network/ai/v1"
   export OPENAI_API_KEY="ob_live_YOUR_KEY"
   
   codex -m deepseek/deepseek-v4.1-flash

   Copy to install

   The SDK takes the same two settings.

   from openai import OpenAI
   
   client = OpenAI(base_url="https://brain.deployd.network/ai/v1", api_key="ob_live_YOUR_KEY")
   client.chat.completions.create(model="deepseek/deepseek-v4.1-flash", messages=[{"role": "user", "content": "Hello"}])

   Copy to install

   The SDK takes the same two settings.

   import OpenAI from "openai";
   
   const client = new OpenAI({ baseURL: "https://brain.deployd.network/ai/v1", apiKey: "ob_live_YOUR_KEY" });
   await client.chat.completions.create({ model: "deepseek/deepseek-v4.1-flash", messages: [{ role: "user", content: "Hello" }] });

   Copy to install

   Paste these into its model-provider settings.

   Base URL   https://brain.deployd.network/ai/v1
   API key    ob_live_YOUR_KEY
   Model      deepseek/deepseek-v4.1-flash

   Copy settings