Models

Below are the list of models from Deca:

Latest models (2.5)

Using Deca Models

Once you have selected a model, this guide will provide the necessary steps to begin using the Deca API.

1. Get Your API Key

Sign in to the GenLabs dashboard and navigate to the API Keys page. Click the Create button to generate a new key. Copy this key and store it securely, as you will need it for all API requests.

Don't have an account? Sign up for free.

2. Fire Up a Request

curl https://api.genlabs.dev/deca/v1/chat/completions \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deca-2.5-ultra-preview",
    "messages": [
      { "role": "user", "content": "Write acrostic about Deca, a powerful AI model" }
    ]
  }'

                  from openai import OpenAI
client = OpenAI(
  base_url = "https://api.genlabs.dev/deca/v1",
  api_key = "YOUR_API_KEY"
)
completion = client.chat.completions.create(
  model="deca-2.5-ultra-preview",
  messages=[
    {
      "role": "user",
      "content": "Write acrostic about Deca, a powerful AI model"
    }
  ]
)

print(completion.choices[0].message.content)

                  
                

Substitute deca-2.5-ultra-preview with any model or snapshot from the table above.

Tips:

• Deca's API is compatible with OpenAI. Set the base_url to https://api.genlabs.dev/deca/v1
• For complex tasks or large models (especially Ultra), use stream: true to prevent time-outs.

3. Parameters Cheat-Sheet

* The default maximum tokens is calculated by context - input. For example, if you send 10,000 tokens to Deca 2.5 Pro (128,000 context), the default max tokens will be 128,000 - 10,000 = 118,000 tokens.

4. Counting (and Saving) Tokens

Prices are shown as $ / MTok – that’s per million tokens. For a ten-token “What are the best hotels in Italy?”, you’ll pay roughly the cost of finding a penny on the sidewalk. Use the cheaper :free snapshots for testing, then move up when you feel you're ready for production.

Rate Limits (Beta)

6. Error Codes That Matter

• 401 Unauthorized – Your API key is missing, invalid, or expired.
• 429 Too Many Requests – You have exceeded the rate limit. Please refer to the Rate Limits section.
• 500, 502, 503, 504 – An internal server error occurred. Please try your request again after a brief delay.