SelamGPT

Welcome

Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.

1from openai import OpenAI
2import os
3client = OpenAI(
4    api_key=os.environ.get("SELAM_API_KEY"),
5    base_url="https://api.selamgpt.com/v1",
6)
7
8response = client.responses.create(
9    input="Explain the importance of fast language models",
10    model="selam-turbo",
11)
12print(response.output_text)

API Overview

The Selam API provides OpenAI-compatible endpoints for chat completions, image generation, text-to-speech, voice agents, translation, file processing, and web search. Built for speed and reliability, our API makes it easy to integrate advanced AI capabilities into your applications.

Base URL

https://api.selamgpt.com/v1

All API requests should be made to this base URL. Authentication is required using an API key in the Authorization header.

Authentication

The Selam API uses API keys for authentication. Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Access is controlled through a tier system (FREE, BETA, PRO) with different rate limits and features. Learn more in the Authentication guide.

Key Features

Chat Completions

Generate text with streaming support, multi-turn conversations, vision capabilities, and function calling.

Image Generation

Create images with 34+ models including Selam-Image and Selam-Image-Pro. Multiple sizes and formats supported.

Text-to-Speech

Convert text to natural speech in Amharic, Somali, Tigrinya, Oromo, and English with 9 unique voices.

Voice Agents

Build real-time voice applications with WebSocket support, interruption handling, and multilingual capabilities.

Multilingual Support

Models support Ethiopian languages (Amharic, Tigrinya, Oromo, Afar, Somali) with auto-detection or target language modes.

File Processing

Upload and process PDFs, documents, images, and 40+ code file types with automatic OCR extraction.

Web Search

Access real-time information with built-in web search using Selam-Search or search tool integration.

Batch Processing

Process multiple requests efficiently with the batch endpoint for cost optimization and bulk operations.

Streaming

Get real-time responses with Server-Sent Events (SSE) for chat completions and translations.

Browse models

View all
selam-coder

Selam-Coder

The best model for coding and agentic tasks across domains

selam-thinking

Selam-Thinking

A faster, cost-efficient version of Selam for well-defined tasks

selam-turbo

Selam-Turbo

Fastest, most cost-efficient version of Selam optimized for latency

Start building

Quick Start

Get started with the SelamGPT API

Models

See all the models SelamGPT offers

API Reference

Explore all API endpoints