qubrid-examples

100+ OSS models with one OpenAI-compatible API.

A focused set of OpenAI-compatible API examples for Qubrid AI. Use the same OpenAI client patterns and point them at https://platform.qubrid.com/v1 to access models like DeepSeek, Qwen, Llama, Mistral, Kimi and more.

Quickstart

Export your Qubrid key:

export QUBRID_API_KEY="your_api_key_here"

Use OpenAI-compatible clients with the Qubrid base URL:

Examples (API code)

Python example

from openai import OpenAI

client = OpenAI(
    base_url="https://platform.qubrid.com/v1",
    api_key="QUBRID_API_KEY",
)

stream = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Flash",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
    max_tokens=393216,
    temperature=1,
    top_p=1,
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

print("\n")

JavaScript example

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://platform.qubrid.com/v1',
  apiKey: 'QUBRID_API_KEY',
});

const stream = await client.chat.completions.create({
  model: 'deepseek-ai/DeepSeek-V4-Flash',
  messages: [
    { role: 'user', content: 'Explain quantum computing in simple terms' }
  ],
  max_tokens: 393216,
  temperature: 1,
  top_p: 1,
  stream: true,
});

for await (const chunk of stream) {
  if (chunk.choices[0]?.delta?.content) {
    process.stdout.write(chunk.choices[0].delta.content);
  }
}

console.log('\n');

Go example

package main

import (
  "bytes"
  "encoding/json"
  "net/http"
)

func main() {
  url := "https://platform.qubrid.com/v1/chat/completions"

  payload := map[string]interface{}{
    "model": "deepseek-ai/DeepSeek-V4-Flash",
    "messages": []map[string]string{
      {"role": "user", "content": "Explain quantum computing in simple terms"},
    },
    "temperature": 1,
    "max_tokens": 393216,
    "stream": true,
    "top_p": 1,
  }

  jsonData, _ := json.Marshal(payload)
  req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
  req.Header.Set("Authorization", "Bearer QUBRID_API_KEY")
  req.Header.Set("Content-Type", "application/json")

  client := &http.Client{}
  _, _ = client.Do(req)
}

curl example

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-ai/DeepSeek-V4-Flash",
  "messages": [
    {"role": "user", "content": "Explain quantum computing in simple terms"}
  ],
  "temperature": 1,
  "max_tokens": 393216,
  "stream": true,
  "top_p": 1
}'

Run an example in python/, javascript/, go/, or curl/.
Swap model for the OSS model you want to use.

Installation

Python

pip install openai

JavaScript / TypeScript

npm install openai

Go

go get github.com/sashabaranov/go-openai

curl

curl is available on most systems and works with the HTTP examples.

Repository structure

qubrid-examples/
│
├── chat/
│   ├── python/
│   ├── javascript/
│   ├── go/
│   └── curl/
│
├── vision/
│   ├── python/
│   ├── javascript/
│   └── curl/
│
├── voice/
│   ├── text-to-speech/
│   └── speech-to-text/
│
├── ocr/
│   ├── python/
│   └── curl/
│
├── embeddings/
│
├── README.md
├── LICENSE
└── .gitignore

Supported models

Qubrid delivers 100+ open-source and commercial models through a single OpenAI-compatible API. Example supported models include:

deepseek-ai/DeepSeek-V4-Flash
deepseek-ai/DeepSeek-V4-Pro
deepseek-ai/DeepSeek-V3
deepseek-ai/DeepSeek-R1-0528
qwen/qwen3-Plus
qwen/qwen3-Flash
qwen/qwen3-Max
qwen/qwen3-VL-Plus
qwen/qwen3-VL-Flash
qwen/qwen3-Coder-Plus
qwen/qwen3-Coder-Flash
qwen/qwen3-Coder-Next
qwen/qwen3-Next
mistralai/Mistral-7B-Instruct-v0.3
moonshotai/Kimi-K2.6
moonshotai/Kimi-K2-Thinking
moonshotai/Kimi-K2-Instruct
moonshotai/Kimi-K2.5
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
google/gemini-3.1-pro-preview
google/gemini-3-flash-preview
google/gemini-2.5-pro
google/gemini-2.5-flash
anthropic/claude-opus-4-7
anthropic/claude-opus-4-6
anthropic/claude-opus-4-5
anthropic/claude-sonnet-4-6
anthropic/claude-haiku-4-5-20251001
openai/gpt-4o
openai/gpt-4o-mini
openai/gpt-4.1
openai/gpt-5.4
openai/gpt-5.4-mini
openai/gpt-5.4-nano
meta-llama/Llama-3.3-70B-Instruct
microsoft/Fara-7B
tencent/HunyuanOCR
zai-org/GLM-4.7
zai-org/GLM-5
miniMaxAI/MiniMax-M2.5

Replace the model field to target any compatible OSS model supported by Qubrid.

Examples index

This repository contains ready-to-run examples organized by capability and language. Click files to open examples.

Chat

Vision (image understanding)

Voice - Text-to-Speech

curl: voice/text-to-speech/curl/tts.sh
Python: voice/text-to-speech/python/tts.py
JavaScript: voice/text-to-speech/javascript/tts.js
Go: voice/text-to-speech/go/tts.go

Voice - Speech-to-Text

curl: voice/speech-to-text/curl/transcribe.sh
Python: voice/speech-to-text/python/transcribe.py
JavaScript: voice/speech-to-text/javascript/transcribe.js
Go: voice/speech-to-text/go/transcribe.go

OCR (basic / layout-preserving)

curl basic: ocr/curl/basic/ocr.sh
curl layout: ocr/curl/layout/ocr_layout.sh
python basic: ocr/python/basic/ocr.py
python layout: ocr/python/layout/ocr_layout.py
javascript basic: ocr/javascript/basic/ocr.js
javascript layout: ocr/javascript/layout/ocr_layout.js
go basic: ocr/go/basic/ocr.go
go layout: ocr/go/layout/ocr_layout.go

Embeddings

See embeddings/

How to run examples

Run curl examples (make executable):

chmod +x path/to/example.sh
./path/to/example.sh

Run Python examples (install requests):

python3 path/to/example.py

Run JavaScript examples (Node.js may require a fetch polyfill):

node path/to/example.js

Run Go examples:

go run path/to/example.go

Switch from OpenAI

Qubrid is an OpenAI-compatible API layer, so you can keep the same request shapes and client patterns. The main change is the target endpoint and the API key source.

Keep the same OpenAI SDK or REST payloads.
Replace the OpenAI endpoint with https://platform.qubrid.com/v1.
Use QUBRID_API_KEY for authentication.
Keep the model, messages, and other request fields the same.

Python migration example

# Existing OpenAI usage
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

# Qubrid usage
client = OpenAI(
    base_url="https://platform.qubrid.com/v1",
    api_key=os.getenv("QUBRID_API_KEY"),
)

JavaScript migration example

// Existing OpenAI usage
const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

// Qubrid usage
const client = new OpenAI({
  baseURL: 'https://platform.qubrid.com/v1',
  apiKey: process.env.QUBRID_API_KEY,
});

Contributing

We welcome contributions that improve examples, expand model coverage, or add integrations.

Open issues for bug reports or missing examples.
Submit PRs with focused changes.
Keep code idiomatic and dependency minimal.
Add docs for new examples or runtime requirements.

Community & docs

Documentation: https://docs.platform.qubrid.com/
Community / Discord: https://discord.com/invite/Btsqxa6ZnQ

License

This repository is licensed under the MIT License.

Chat completion fields

Use these fields in any language when making Qubrid chat completion requests.

Authorization (header, required): Bearer <token>
model (string, required): The language model to use.
messages (array, required): Conversation messages in chat format.
max_tokens (integer): Maximum number of tokens to generate.
temperature (number): Controls randomness in output.
top_p (number): Nucleus sampling parameter.
stream (boolean): Whether to stream responses incrementally.

Example chat message structure:

{
  "model": "openai/gpt-oss-120b",
  "messages": [
    {"role": "user", "content": "Summarize this support ticket into bullet-point next steps for the agent."}
  ],
  "max_tokens": 4096,
  "temperature": 0.7,
  "top_p": 1,
  "stream": true
}

Voice - Text-to-Speech

Convert text into natural-sounding speech using AI voice models.

Endpoint: POST /v1/audio/generations
Authorization: Bearer <token> (header)
Body (application/json):
- model (string, required) - TTS model to use. Example: qwen3-tts-flash
- text (string, required) - Text to synthesize.
- voice (string, required) - Voice preset. Example: Cherry
- language_type (string) - Language setting, e.g. Auto

Response (200 application/json):

{
  "created": 1710000000,
  "data": [
    { "url": "https://cdn.qubrid.com/generated/audio.mp3" }
  ]
}

Speech-to-Text - Transcription

Transcribe audio files to text.

Endpoint: POST /api/v1/qubridai/audio/transcribe
Authorization: Bearer <token> (header)
Body: multipart/form-data
- file (file, required) - Audio file (wav, mp3, etc.)
- model (string, required) - STT model. Example: openai/whisper-large-v3

Response (200 application/json):

{
  "text": "Today is a wonderful day to build something people love!"
}

Vision - Multimodal

Use vision-language models to analyze images via chat-style requests.

Endpoint: POST /v1/chat/completions
Authorization: Bearer <token> (header)
Body (application/json):
- model (string, required) - Example: Qwen/Qwen3-VL-Plus
- messages (array, required) - Chat-style payload that can include text and image items.
- max_tokens (integer, default: 16384)
- temperature (number, default: 0.1)
- top_p (number, default: 1)
- stream (boolean, default: true)

Response (200 application/json): standard OpenAI-compatible chat completion response or streamed chunks. Example fields:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "Qwen/Qwen3-VL-Plus",
  "choices": [{ "index": 0, "message": { /* ... */ }, "finish_reason": "stop" }],
  "usage": { "prompt_tokens": 120, "completion_tokens": 48, "total_tokens": 168 },
  "x_metrics": { "ttft_seconds": 0.41, "tps": 38.4, "total_time_seconds": 1.92 }
}

OCR - Document text extraction

OCR endpoints accept chat-style image inputs and return extracted text. Use the OCR-specialized vision model for best results.

Endpoint: POST /v1/chat/completions
Authorization: Bearer <token> (header)
Body (application/json):
- model (string, required) - Example: Hunyuan/Hunyuan-OCR-1B
- messages (array, required) - Chat-style input with text instructions and image content
- max_tokens (integer, default: 8192)
- temperature (number, default: 0.1)
- top_p (number, default: 1)
- stream (boolean, default: false)

Response (200 application/json): standard chat completion response containing extracted text and metadata:

{
  "id": "chatcmpl-ocr-123456",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "Hunyuan/Hunyuan-OCR-1B",
  "choices": [{ "index": 0, "message": { /* extracted text */ }, "finish_reason": "stop" }]
}

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

qubrid-examples

Quickstart

Examples (API code)

Python example

JavaScript example

Go example

curl example

Installation

Python

JavaScript / TypeScript

Go

curl

Repository structure

Supported models

Examples index

How to run examples

Switch from OpenAI

Python migration example

JavaScript migration example

Contributing

Community & docs

License

Chat completion fields

Voice - Text-to-Speech

Speech-to-Text - Transcription

Vision - Multimodal

OCR - Document text extraction

About

Uh oh!

Releases

Packages

Uh oh!

Contributors

Uh oh!

Languages

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
chat		chat
ocr		ocr
vision		vision
voice		voice
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md

Folders and files

Latest commit

History

Repository files navigation

qubrid-examples

Quickstart

Examples (API code)

Python example

JavaScript example

Go example

curl example

Installation

Python

JavaScript / TypeScript

Go

curl

Repository structure

Supported models

Examples index

How to run examples

Switch from OpenAI

Python migration example

JavaScript migration example

Contributing

Community & docs

License

Chat completion fields

Voice - Text-to-Speech

Speech-to-Text - Transcription

Vision - Multimodal

OCR - Document text extraction

About

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Packages