Vora Cloud

Set up your agent

Every tool needs the same three settings.

Agents send long prompts and rely on tool calling. The context window is 16,384 tokens, so small, focused tasks work best.

OpenCode

Add a provider to opencode.json. Pick the model with /models.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "vora": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Vora Cloud",
      "options": {
        "baseURL": "https://api.voracompute.com/v1",
        "apiKey": "{env:VORA_API_KEY}"
      },
      "models": {
        "qwen3.5-9b": {
          "name": "Qwen3.5 9B"
        }
      }
    }
  },
  "model": "vora/qwen3.5-9b"
}

Cline

In Cline's settings:

  1. API Provider: OpenAI Compatible
  2. Base URL: https://api.voracompute.com/v1
  3. OpenAI Compatible API Key: your key
  4. Model ID: qwen3.5-9b

Continue

Add a model to config.yaml. Put VORA_API_KEY=vora_sk_... in ~/.continue/.env.

name: My Config
version: 0.0.1
schema: v1
models:
  - name: Qwen3.5 9B (Vora)
    provider: openai
    model: qwen3.5-9b
    apiBase: https://api.voracompute.com/v1
    apiKey: ${{ secrets.VORA_API_KEY }}

Aider

The openai/ prefix tells Aider to use an OpenAI-compatible API.

aider --openai-api-base https://api.voracompute.com/v1 \
  --openai-api-key $VORA_API_KEY \
  --model openai/qwen3.5-9b

LangChain

import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.voracompute.com/v1",
    api_key=os.environ["VORA_API_KEY"],
    model="qwen3.5-9b",
)

LlamaIndex

Install llama-index-llms-openai-like.

import os
from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="qwen3.5-9b",
    api_base="https://api.voracompute.com/v1",
    api_key=os.environ["VORA_API_KEY"],
    context_window=16384,
    is_chat_model=True,
    is_function_calling_model=True,
)

Vercel AI SDK

Install ai and @ai-sdk/openai-compatible.

import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { generateText } from "ai";

const vora = createOpenAICompatible({
  name: "vora",
  baseURL: "https://api.voracompute.com/v1",
  apiKey: process.env.VORA_API_KEY,
});

const { text } = await generateText({ model: vora("qwen3.5-9b"), prompt: "Hello" });