Documentation Index

Fetch the complete documentation index at: https://docs.123api.co/llms.txt Use this file to discover all available pages before exploring further.

123API — OpenAI-Compatible API Gateway (GPT-5, Claude, Gemini)

OpenAI-compatible API for GPT-5, Claude, Gemini. Unified routing, transparent pricing, low latency, SDK support and pay-as-you-go access.

One unified OpenAI-compatible endpoint for GPT-5, Claude and Gemini. Migrate from OpenAI in minutes by simply changing your base URL to https://123api.co/v1 and replacing your API key. Keep your existing SDKs with no code rewrite. Unified routing helps improve availability and keeps latency predictable across common text, image, video and audio workflows.

Quick Start

OpenAI-Compatible Endpoints

123API provides OpenAI-style endpoints for seamless migration. Simply change your base URL and keep using your existing SDKs. Core interfaces follow OpenAI standards with extended support for Claude, Gemini, Sora and VEO style workflows.

Chat Completion API

Chat completion with GPT-5, GPT-4o, Claude Sonnet 4.5 and Gemini 2.0 Flash. OpenAI-compatible API with streaming support and low latency.

Image Creation API

Image creation with GPT-4o Image and Gemini image models. OpenAI-style API for seamless integration.

Video Creation API

Video creation with Sora-style and VEO-style models. Async task management with status tracking and webhook-friendly flows.

Platform Benefits

Transparent Pricing

Pay-as-you-go with no subscription required. Clear per-request and per-model billing helps teams control usage without hidden fees.

• Clear pricing for all mainstream models
• Suitable for both testing and production workloads
• No hidden access fees
• Pay only for actual usage

Unified Routing

Use one gateway for text, image, video and audio endpoints. This simplifies integration, environment management and operational maintenance for products that depend on multiple model families.

Stable Access

A single integration layer makes it easier to standardize retries, monitoring and fallback handling across your applications.

Low Latency Delivery

Optimized gateway routing helps keep response times predictable for global and domestic access scenarios.

Rate Limit Management

Centralized access makes it easier to distribute traffic, control burst behavior and avoid provider-side throttling issues in business applications.

Real-Time Status

Monitor async task progress for image and video creation workflows and retrieve results when tasks complete. Check Status →

SDKs & Code Examples

Official SDK usage remains OpenAI-compatible, allowing seamless migration by changing only the base URL configuration.

Python SDK

Install with pip install openai. Set base URL and use your existing OpenAI code without major changes.

from openai import OpenAI
 
client = OpenAI(
    base_url="https://123api.co/v1",
    api_key="your-123api-key"
)

Node.js SDK

Install with npm install openai. Configure baseURL to the 123API endpoint and keep your current integration style.

import OpenAI from 'openai';
 
const client = new OpenAI({
  baseURL: 'https://123api.co/v1',
  apiKey: 'your-123api-key'
});

Java SDK

Any OpenAI-compatible Java client can work with 123API after changing the base URL and API key.

Migration from OpenAI

Switch to 123API in under 5 minutes. No code rewrite needed, just update the base URL and API key.

1. Get Your API Key

   Sign in to the 123API Dashboard and create an API key for your application or environment.

2. Update Base URL

   Change the OpenAI base URL to https://123api.co/v1. Your existing SDK integration should continue to work with minimal changes.

3. Test Your Endpoints

   Run your existing code with the new base URL and confirm model availability, latency and billing behavior in your dashboard.

Supported Models via Unified Endpoint

Access mainstream providers through one OpenAI-compatible gateway. All models are exposed with a consistent request and response style.

Chat Completion Models

Leading language models for chat, completion and code tasks:

• GPT-5: OpenAI flagship model with stronger reasoning
• GPT-4o & GPT-4o Mini: Multimodal models balancing performance and cost
• Claude Sonnet 4.5 & Haiku 4.5: Anthropic models for complex reasoning
• Gemini 2.0 Flash & Flash Thinking: Google multimodal models

Image Creation Models

Image creation from text prompts:

• GPT-4o Image: OpenAI image generation model
• Gemini Image Series: Fast and flexible image generation options

Video Creation Models

Video creation with async task tracking and webhook-friendly workflows:

• Sora-style Models: Video generation workflows compatible with async tasks
• VEO-style Models: Video generation with task-based result retrieval

Speech Models

Speech-to-text and text-to-speech via OpenAI-compatible endpoints:

• Whisper-1: Audio transcription model
• TTS: Text-to-speech with multiple voices

FAQ

Explore More