Skip to main content
Qubrid AI
MistralAI · Chat / LLM · 7.3B Parameters · 32K ContextQubrid Playground License HuggingFaceStreaming Instruction Following Code Chat

Overview

Mistral 7B Instruct v0.3 is a 7.3B parameter language model celebrated for its efficiency, outperforming larger models on many benchmarks. The v0.3 instruct version is specifically fine-tuned for chat and instruction-following tasks — delivering fast, high-quality responses with a remarkably low memory footprint. Whether you’re building customer-facing assistants, developer tooling, or content pipelines, Mistral 7B v0.3 offers an outstanding performance-to-cost ratio.
🏎️ Fast inference. Low cost. High accuracy. — Get started on the Qubrid AI Serverless API for just $0.21 / 1M input tokens.

Model Specifications

FieldDetails
Model IDmistralai/Mistral-7B-Instruct-v0.3
ProviderMistralAI
KindChat / LLM
Parameters7.3B
Context Length32,768 Tokens
MoENo
LicenseApache 2.0
Function CallingNot Supported
Image SupportN/A
Serverless APIAvailable
Fine-tuningComing Soon
On-demandComing Soon
State🟢 Ready

Pricing

💳 Access via the Qubrid AI Serverless API with pay-per-token pricing. No infrastructure management required.
Token TypePrice per 1M Tokens
Input Tokens$0.21
Output Tokens$0.25

Quickstart

Prerequisites

  1. Create a free account at platform.qubrid.com
  2. Generate your API key from the API Keys section
  3. Replace QUBRID_API_KEY in the code below with your actual key

Python

from openai import OpenAI

# Initialize the OpenAI client with Qubrid base URL
client = OpenAI(
  base_url="https://platform.qubrid.com/v1",
  api_key="QUBRID_API_KEY",
)

# Create a streaming chat completion
stream = client.chat.completions.create(
  model="mistralai/Mistral-7B-Instruct-v0.3",
  messages=[
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  max_tokens=4096,
  temperature=0.7,
  top_p=1,
  stream=True
)

# If stream = False comment this out
for chunk in stream:
  if chunk.choices and chunk.choices[0].delta.content:
      print(chunk.choices[0].delta.content, end="", flush=True)
print("\n")

# If stream = True comment this out
print(stream.choices[0].message.content)

JavaScript

import OpenAI from "openai";

// Initialize the OpenAI client with Qubrid base URL
const client = new OpenAI({
  baseURL: "https://platform.qubrid.com/v1",
  apiKey: "QUBRID_API_KEY",
});

// Create a streaming chat completion
const stream = await client.chat.completions.create({
  model: "mistralai/Mistral-7B-Instruct-v0.3",
  messages: [
    {
      role: "user",
      content: "Explain quantum computing in simple terms",
    },
  ],
  max_tokens: 4096,
  temperature: 0.7,
  top_p: 1,
  stream: true,
});

// If stream = false comment this out
for await (const chunk of stream) {
  if (chunk.choices[0]?.delta?.content) {
    process.stdout.write(chunk.choices[0].delta.content);
  }
}
console.log("\n");

// If stream = true comment this out
console.log(stream.choices[0].message.content);

Go

package main

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

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

	data := map[string]interface{}{
		"model": "mistralai/Mistral-7B-Instruct-v0.3",
		"messages": []map[string]string{
			{
				"role":    "user",
				"content": "Explain quantum computing in simple terms",
			},
		},
		"temperature": 0.7,
		"max_tokens":  4096,
		"stream":      true,
		"top_p":       1,
	}

	jsonData, _ := json.Marshal(data)
	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{}
	res, _ := client.Do(req)
	defer res.Body.Close()

	scanner := bufio.NewScanner(res.Body)
	for scanner.Scan() {
		line := scanner.Text()
		if line != "" {
			fmt.Println(line)
		}
	}
}

cURL

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistralai/Mistral-7B-Instruct-v0.3",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 4096,
  "stream": true,
  "top_p": 1
}'

Live Example

Prompt: Explain quantum computing in simple terms
Response:
Quantum computing uses the principles of quantum mechanics to process
information in ways classical computers cannot.

Classical computers work with bits — each is either 0 or 1.
Quantum computers use qubits, which can be 0, 1, or both at the
same time (superposition).

This means a quantum computer can explore many solutions simultaneously
rather than one at a time — making it exponentially faster for
certain types of problems:

  - Breaking and building encryption
  - Simulating molecules for drug discovery
  - Optimizing large-scale logistics and finance problems

Another key property: entanglement — two qubits can be linked so
that measuring one instantly tells you something about the other,
no matter the distance between them.

Quantum computers aren't replacing laptops. They're a specialized
tool for problems classical machines would take millions of years
to solve.
Try it yourself in the Qubrid AI Playground →

Playground Features

The Qubrid AI Playground lets you chat with Mistral 7B v0.3 instantly — no setup, no code, no cost to explore.

🧠 System Prompt

Lock in the model’s role, tone, and rules before the conversation starts. Great for building focused assistants without touching any code.
Example: "You are a helpful customer support agent for a SaaS product.
Answer only questions related to the product. Be concise, friendly,
and always end with: 'Is there anything else I can help you with?'"
Set your system prompt once in the Qubrid Playground and it applies across every turn of the conversation.

🎯 Few-Shot Examples

Guide the model’s output style with concrete examples — no fine-tuning, no retraining required.
User InputAssistant Response
Summarize this in one sentence: [long article]The article discusses how renewable energy adoption is accelerating globally, driven by falling costs and government incentives.
Write a subject line for a re-engagement emailWe miss you — here's 20% off to come back
💡 Add few-shot examples directly in the Qubrid Playground to dial in tone, format, and domain focus instantly.

Inference Parameters

ParameterTypeDefaultDescription
StreamingbooleantrueEnable streaming responses for real-time output
Temperaturenumber0.7Controls randomness. Higher values mean more creative but less predictable output
Max Tokensnumber4096Maximum number of tokens to generate in the response
Top Pnumber1Nucleus sampling: considers tokens with top_p probability mass

Use Cases

  1. Customer-facing chatbots and virtual assistants that handle FAQs and multi-turn dialogue
  2. Long-form and short-form content generation such as blogs, emails, and product descriptions
  3. Developer code assistance for completion, explanation, and small refactors
  4. General question answering over product, documentation, or knowledge-base content
  5. Summarization of long documents, transcripts, and knowledge-dense articles

Strengths & Limitations

StrengthsLimitations
Fast inference speedSmaller context window compared to largest models
Low memory footprintCan struggle with highly complex, multi-step reasoning
Excellent instruction followingFunction calling not supported
High performance relative to its size

Why Qubrid AI?

  • 🚀 No infrastructure setup — serverless API, pay only for what you use
  • 🔁 OpenAI-compatible — drop-in replacement using the same SDK, just swap the base URL
  • Speed-optimized serving — Mistral 7B’s low footprint meets Qubrid’s low-latency infrastructure
  • 🧪 Built-in Playground — prototype with system prompts and few-shot examples instantly at platform.qubrid.com
  • 📊 Full observability — API logs and usage tracking built into the Qubrid dashboard
  • 🌐 Multi-language support — Python, JavaScript, Go, cURL out of the box

Resources

ResourceLink
📖 Qubrid Docsdocs.platform.qubrid.com
🎮 PlaygroundTry Mistral 7B v0.3 live
🔑 API KeysGet your API Key
🤗 Hugging Facemistralai/Mistral-7B-Instruct-v0.3
💬 DiscordJoin the Qubrid Community

Built with ❤️ by Qubrid AI

Frontier models. Serverless infrastructure. Zero friction.