Documentation
Integrate Velqa like any OpenAI-compatible API, and learn every feature of the product.
Base configuration
base_url = "https://api.velqa.dev/v1"
api_key = "sk-..."
Getting started
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.
Get started with velqa.dev in 2 minutes
Velqa.dev is an OpenAI-compatible API gateway for open-weight models. At launch, checkout is Stripe in USD for US customers; Moroccan local-currency billing...
Velqa API authentication — `sk-...` key and Bearer header
Every request to the Velqa API authenticates with an API key of the form sk-..., passed in the Authorization: Bearer HTTP header. That's the only secret the...
Chat / LLM
Chat / LLM with Velqa — OpenAI-compatible API
Velqa's chat API follows the OpenAI POST /v1/chat/completions format exactly. To use it from existing code, just change the base_url to https://api.velqa.dev...
Streaming responses with Velqa — SSE, OpenAI-compatible
Velqa can return chat responses as a stream: tokens arrive as they're generated, via Server-Sent Events (SSE). This is ideal for a chat-style UI where you wa...
Tool calling / function calling with Velqa — OpenAI style
Tool calling lets a model call your functions: you describe tools in the tools parameter, the model replies with tool_calls, you run the matching function, t...
Velqa's Anthropic-compatible API — `/v1/messages` endpoint
On top of the OpenAI-compatible API, Velqa exposes an Anthropic-compatible endpoint: https://api.velqa.dev/v1/messages. Tools and SDKs built for Anthropic (i...
Inference APIs
Embeddings with Velqa.dev
Velqa offers two multilingual embedding models (strong in French and Arabic), ideal for semantic search, RAG and document comparison. They are available on t...
Reranking with Velqa.dev — reorder your RAG results (FR / AR)
Velqa offers multilingual reranking via qwen3-reranker-8b (Alibaba), on the API https://api.velqa.dev/v1/rerank. The reranker takes a query and a list of doc...
Build a RAG pipeline on Velqa.dev — embeddings, pgvector and reranking
A RAG pipeline answers questions from your own documents. Velqa serves the three model calls — embedding, reranking, chat — behind a single API key.
Image generation (text-to-image) with Velqa.dev
Velqa offers image generation on the OpenAI-compatible API https://api.velqa.dev/v1/images/generations, with three Black Forest Labs models covering drafts,...
Audio transcription (Speech-to-Text) with Velqa.dev
Velqa offers audio transcription via whisper-large-v3 (multilingual, strong in French / Arabic / darija), on the OpenAI-compatible API https://api.velqa.dev/...
Text-to-Speech with Velqa.dev
Velqa offers text-to-speech on the OpenAI-compatible API https://api.velqa.dev/v1/audio/speech. You send text and a voice, and the API returns the audio byte...
Dashboard
The velqa.dev dashboard — manage your account and API keys
The velqa.dev dashboard puts everything a developer needs in one place: create API keys, try models with no code, track your spend, and manage your balance....
velqa.dev API keys — create, limit, and revoke keys
Your sk-... API keys authenticate every request to velqa.dev. This guide covers creating a key from the dashboard, restricting which models it can call, sett...
Track your velqa.dev usage — spend, history, and live quota
The dashboard's Usage section shows where your budget goes: spend this month, daily breakdown by model, cost per project, a detailed request history, and a r...
velqa.dev Playground — try models with no API key or card
The Playground lets you try velqa.dev models right in the browser, with no code. It's available publicly at /playground (no sign-up, with a demo quota) and f...
Billingbeta
velqa.dev plans & pricing — subscriptions and Recharge Boost
Velqa offers three monthly subscriptions (Starter, Dev, Pro) and a prepaid pay-as-you-go mode (Recharge Boost). At launch, checkout is Stripe USD for US cust...
velqa.dev Recharge Boost — top up your USD balance via Stripe
Recharge Boost is Velqa's prepaid pay-as-you-go balance: you pick a USD amount, pay through Stripe, and the credit is added to your balance to use every mode...
Automatic fallback to Boost on velqa.dev — stop getting blocked when your subscription runs out
Automatic fallback to Boost is a toggle that lets your spend spill over to your prepaid Boost balance when your subscription (Base) limits are exhausted, ins...
Auto top-up and low-balance alerts on velqa.dev — never run out of credit
Auto top-up saves a card and recharges your Boost balance as soon as it drops below a threshold you set; a low-balance email alert also warns you when the ba...
Currency and billing on velqa.dev — USD
At launch, Velqa bills in US dollars (USD) through Stripe for US customers. The amount shown at Stripe Checkout is the amount charged. Moroccan local-currenc...
Sandbox Agentbeta
Velqa Sandbox Agent — run code in an ephemeral Docker sandbox (BETA)
Velqa's Sandbox Agent lets you build AI agents that actually run code inside an isolated, ephemeral Docker sandbox, straight from the dashboard. This is a BE...
Create and configure a Sandbox agent (BETA)
An agent is a reusable profile you set up once and then start as many times as you need. It defines the persona and environment of your Sandbox conversations...
Sandbox Agent conversations and turns (BETA)
Once you've configured an agent, you talk to it through conversations made of turns. Each turn spins up an ephemeral Docker sandbox where the agent does its...
Sandbox Agent tools (BETA)
Inside the sandbox, the agent doesn't just reply — it calls tools to act. During a turn, every tool call shows up live in the UI. This page describes the too...
Sandbox Agent workspace and artifacts (BETA)
Every sandbox has a workspace: the folder where files live during a turn. You can upload your own files for the agent to process, and the agent can publish a...
Page Agentbeta
Tool integrations
Tool integrations — connect your coding agents to Velqa
Velqa exposes an OpenAI-compatible API, so any OpenAI-compatible client (opencode, Cline, Roo Code, Kilo Code, Continue…) works with no plugin: you just chan...
Use Claude Code with MiniMax M3 or DeepSeek — velqa.dev
Configure Claude Code to use DeepSeek or MiniMax M3 through velqa.dev. At launch, checkout is available in USD through Stripe for US customers; Moroccan loca...
Use MiniMax M3 with opencode — velqa.dev
Configure opencode to use MiniMax M3 through velqa.dev. At launch, checkout is Stripe in USD for US customers.
Use MiniMax M3 with Cline — velqa.dev
Configure the Cline VS Code extension to use velqa.dev models. At launch, checkout is Stripe in USD for US customers.
Use MiniMax M3 with Roo Code — velqa.dev
Roo Code is a fork of Cline with advanced mode profiles (Code, Architect, Ask, Debug). It is configured the same way for an OpenAI-compatible provider.
Use MiniMax M3 with Kilo Code — velqa.dev
Kilo Code is an OpenAI-compatible VS Code coding agent. Configure it in a few fields to use velqa.dev; launch checkout is Stripe in USD for US customers.
Use MiniMax M3 with Continue — velqa.dev
Continue is an open-source VS Code and JetBrains extension for chat, inline editing and agent workflows against the model of your choice. Pointing it at velq...
Account
velqa.dev account — sign up, sign in, and verify your email
Creating a velqa.dev account takes seconds: email and password, or sign in with Google or GitHub. This guide covers registration, email verification (require...
velqa.dev settings — profile, language, ICE, and balance alerts
The dashboard's Settings section holds your account configuration: profile and organization details, dashboard language, billing address with ICE for Morocca...
velqa.dev referrals — earn $1 for every developer you invite
The Referrals program rewards developers who spread the word about velqa.dev: your referred user gets $1 and you get $1 on their first payment. This guide ex...
Reference
Models available on velqa.dev
All the models below are reachable through velqa.dev's OpenAI-compatible API (https://api.velqa.dev/v1/chat/completions) and Anthropic-compatible API (https:...
Rate limits and budgets on Velqa.dev
Velqa applies per-key API limits to protect your balance and smooth out load: a maximum throughput (RPM / TPM) per model, and a monthly USD budget per key. T...
Velqa.dev API error codes and how to fix them
A rundown of the HTTP errors returned by the OpenAI-compatible API https://api.velqa.dev/v1, their most common cause and the fix to apply. Every error respon...