The velqa-auto model — automatic chat routing based on your plan

velqa-auto is a virtual model ID: send "model": "velqa-auto" and Velqa automatically routes your chat request to a suitable model, using a heuristic classifier. It's the good default when you don't want to pick a model by hand. Like everything else, it's payable in dirhams.

How it works

• Velqa analyzes your request (task type, length…) and selects an appropriate model among those available.
• Routing respects your plan: velqa-auto will never pick a model your plan doesn't include. A Starter user is routed among Starter models; a Pro or Recharge Boost user has access to all of them.
• It's chat-only (/v1/chat/completions). There's no auto-routing for embeddings, audio or images — specify an explicit model ID for those.

Example (Python)

from openai import OpenAI

client = OpenAI(base_url="https://api.velqa.dev/v1", api_key="sk-...")

resp = client.chat.completions.create(
    model="velqa-auto",
    messages=[{"role": "user", "content": "Summarize this text in 3 bullet points."}],
)
print(resp.choices[0].message.content)

Example (curl)

curl https://api.velqa.dev/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"velqa-auto","messages":[{"role":"user","content":"Hello"}]}'

When to use it

• Use `velqa-auto` for general-purpose apps, prototypes, or when your requests are heterogeneous and you want a good cost/quality trade-off without managing selection.
• Specify an explicit model when you need reproducible behavior, a specific model for heavy coding, or a particular context window. See the models list.

See also: chat overview.