Veritas API

Quickstart

The Veritas API is OpenAI-compatible, point your requests at https://veritas.guru/api/v1 and authenticate with your vrt_ key. Chat, images, audio and video all work with the same key.

curl https://veritas.guru/api/v1/chat/completions \
  -H "Authorization: Bearer vrt_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veritas-uncensored",
    "messages": [
      { "role": "user", "content": "What is Bitcoin?" }
    ]
  }'

Using JavaScript:

const res = await fetch('https://veritas.guru/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer vrt_your_key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'veritas-uncensored',
    messages: [
      { role: 'user', content: 'What is Bitcoin?' }
    ]
  })
});
const data = await res.json();
console.log(data.choices[0].message.content);

Every response includes X-Veritas-Plan and X-Veritas-Requests-Remaining headers so you can track your monthly usage.

Endpoints

All endpoints take a model field. The defaults below are the uncensored Veritas models.

Method	Endpoint	Description	Default model
POST	/api/v1/chat/completions	Chat completion (OpenAI-compatible)	veritas-uncensored
POST	/api/v1/image/generate	Generate an image from a prompt	veritas-image
POST	/api/v1/audio/speech	Text-to-speech (returns audio)	veritas-voice
POST	/api/v1/video/queue	Queue a text-to-video job	veritas-video
POST	/api/v1/video/retrieve	Poll a queued video job for the result	n/a
GET	/api/v1/models	List all available models	n/a
POST	/api/keys/generate	Generate a new API key	n/a

Chat models

Pass any of these as the model on /chat/completions. All uncensored.

Model	Context	Best for
veritas-uncensored	128K	Default. Maximum-freedom general chat.
veritas-roleplay	128K	Creative roleplay and character work.
veritas-private	32K	Confidential computing (runs end-to-end encrypted in a secure enclave).

Image example

curl https://veritas.guru/api/v1/image/generate \
  -H "Authorization: Bearer vrt_your_key" \
  -H "Content-Type: application/json" \
  -d '{ "model": "veritas-image", "prompt": "a lighthouse at dawn", "width": 1024, "height": 1024 }'

Image models: veritas-image (uncensored photorealistic, default) and veritas-image-nsfw (explicit-tuned). All run with content filters off — output is driven entirely by your prompt.

Text-to-speech example

curl https://veritas.guru/api/v1/audio/speech \
  -H "Authorization: Bearer vrt_your_key" \
  -H "Content-Type: application/json" \
  -d '{ "model": "veritas-voice", "input": "Hello from Veritas", "voice": "af_sky" }' \
  --output speech.mp3

Request format

{
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Your message here" }
  ]
}

Response format

{
  "id": "vrt-1234567890",
  "object": "chat.completion",
  "model": "veritas",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 48,
    "total_tokens": 60
  }
}

Authentication

Pass your key in the Authorization header:

Authorization: Bearer vrt_your_key

Error codes

Code	Meaning
401	Invalid or missing API key
429	Monthly request limit reached
500	Server error, try again

Pricing

All plans include uncensored inference and zero data retention.