Skip to main content
Velqa
← Back to home

What is Velqa — the OpenAI-compatible LLM API

Velqa.dev is an OpenAI- and Anthropic-compatible gateway for large language models, including Qwen, DeepSeek, GLM and MiniMax.

The problem Velqa solves

Velqa gives existing applications and coding tools one compatible API surface for those models. Checkout is Stripe, in USD, by international card. Moroccan-issued cards are not accepted here: customers in Morocco are served by velqa.ma, where dirham checkout by Moroccan card opens soon.

What you get

  • An OpenAI-compatible API: https://api.velqa.dev/v1. The same endpoints you already know (/chat/completions, /embeddings, /images/generations…).
  • An Anthropic-compatible API: https://api.velqa.dev/v1/messages, for tools that speak the Anthropic protocol (see Anthropic API).
  • Top-tier open-weight models: Qwen3.7 Max, DeepSeek V4, GLM 5.2, MiniMax M3 and more (full list and pricing: models).
  • Straightforward billing: Starter / Dev / Pro subscriptions and prepaid Recharge Boost (see plans).

Who is it for?

  • Developers and students building with OpenAI- or Anthropic-compatible tools.
  • Teams that want predictable model access and costs.
  • Anyone already using the OpenAI SDK or a coding tool (opencode, Cline, Claude Code…) who just wants to switch providers.

How it fits: two settings

If your code or tool already uses an OpenAI-compatible API, migrating comes down to changing two values:

SettingValue
base_urlhttps://api.velqa.dev/v1
api_keyyour sk-... key
from openai import OpenAI

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

resp = client.chat.completions.create(
    model="minimax-m3",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Next steps