Stability AI

StableLM 2 12B

otherReleased May 2026

Stability AI's 12.1 billion parameter decoder-only language model pre-trained on 2 trillion tokens of diverse multilingual and code datasets. Supports multiple languages and offers strong performance for its compact size with instruction-tuned chat variant available.

Capabilities

chatcompletioncode-generation

Modalities

textcode

Context Window

4K tokens

Providers

available

Available from 1 provider

Cheapest

Hugging Face Inference

$0.20/1M tokens

Hugging Face Inference

Providers (1)

Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.

Provider	Pricing (per 1M)	Rate Limits	Regions	Health	Latency
Hugging Face Inference	In: $0.10Out: $0.10	60 RPM / 200K TPM	us-east-1	Healthy	0ms

Quick Start

Use this model via Hugging Face Inference with an OpenAI-compatible SDK.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.hugging-face.com/v1",
  apiKey: process.env.HUGGING_FACE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "stabilityai/stablelm-2-12b-chat",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

console.log(response.choices[0].message.content);

Using Hugging Face Inference API • OpenAI-compatible SDK