Skip to content

HINOW model

hinow/hinova

HiNova

Intelligence and speed for production.

Best for: Assistants, copilots, and content

Pricing per 1 million tokens

Input

US$ 0,69

per 1 million tokens

Output

US$ 7,49

per 1 million tokens

Integrate nowCompare

Where to use it

  • Customer service and support
  • In-product assistants
  • Content generation and transformation
  • Interactive experiences

How to get started

  1. 1

    Define the outcome

    Describe the task, the context, the quality criteria, and the expected format.

  2. 2

    Test real cases

    Start with hinow/hinova and include common, hard, and incomplete examples.

  3. 3

    Measure before promoting

    Compare quality, latency, tokens, and cost in the application environment.

Example

curl https://api.hinow.ai/v1/chat/completions \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"hinow/hinova","messages":[{"role":"user","content":"Resuma este documento em cinco marcadores e cite as evidências."}]}'

hinow/hinova is served by Chat Completions. Parameters, streaming, system messages, limits, and errors are in Text generation — the full reference for the endpoint, and it applies to all three language models.

When to compare another option

Maximum quality or the lowest unit cost is the dominant requirement.

From the first call to production

The full reference for the endpoint, with parameters, streaming, and errors — plus the table to compare before settling on a default.

Text generationCompare models
Was this page helpful?