RailwailRailwail

Stable Code Instruct 3B

huggingface
Code

Instruction-tuned 3B code model from Stability AI, fine-tuned from stable-code-3b for chat-style coding tasks. Handles code generation, explanation and fix-up across multiple languages and was competitive with larger code models on benchmarks at release.

Try Stable Code Instruct 3B now
Send a single prompt and stream a response inline. Hit Cmd+Enter to submit.
Sign in to try this model with €5 free credits.
Sign in
Press Cmd+Enter to send
Response appears here.
TL;DR·Last updated June 24, 2026

Stable Code Instruct 3B is code AI model from huggingface, priced at €0.500 per 1M input tokens with a 16.4K tokens context window.

About this model

stable-code-instruct-3b is the instruction-tuned variant of Stability AI's stable-code-3b. It was trained for conversational and instruction-following coding tasks such as writing functions from a description, explaining code, and fixing bugs across several popular programming languages. At release Stability reported it scoring competitively with larger 3B-7B code models on MultiPL-E and similar benchmarks. Unlike the base completion checkpoints, it expects an instruction-style prompt.
Try Stable Code Instruct 3B
Sign in to generate — 50 free credits on sign-up

Pricing

Price per Generation
Per generationFree

API Integration

Use our OpenAI-compatible API to integrate Stable Code Instruct 3B into your application.

Install
npm install railwail
JavaScript / TypeScript
import railwail from "railwail";

const rw = railwail("YOUR_API_KEY");

// Simple — just pass a string
const reply = await rw.run("stable-code-instruct-3b", "Hello! What can you do?");
console.log(reply);

// With message history
const reply2 = await rw.run("stable-code-instruct-3b", [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);

// Full response with usage info
const res = await rw.chat("stable-code-instruct-3b", [
  { role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);
Specifications
Context window
16,384 tokens
Developer
huggingface
Category
Code
Supported Formats
text
Tags
code
huggingface
stability-ai
stable-code
instruct
code-generation
open-source
small

Frequently asked questions

Related Models

View all Code

Codestral

Mistral AI

Mistral's code-specialized model. Optimized for code generation, completion, and understanding across 80+ languages.

Free

Code Llama 13B Instruct

Meta

Meta's 13B Code Llama tuned for instruction following. A faster mid-size option for code generation and completion, supporting infilling for inserting code at a cursor position. Served on Replicate per call.

€1.00

Code Llama 34B Instruct

Meta

Meta's 34B Code Llama tuned for instruction following. A balance of size and quality for code generation, completion, and explanation, with strong coverage of Python, JavaScript, and other common languages. Runs on Replicate per call.

€2.00

Code Llama 70B Instruct

Meta

Meta's largest Code Llama, a 70B Llama-2 derivative specialized for programming and tuned to follow instructions in chat form. Handles code generation, completion, and explanation across common languages. Served on Replicate as a per-call endpoint.

€3.00

Start using Stable Code Instruct 3B today

Get started with free credits. No credit card required. Access Stable Code Instruct 3B and 100+ other models through a single API.

Get Started FreeBrowse All Models