Urgent.News

What's breaking now, across thousands of outlets.

AI

Call GPT, Claude, Gemini and DeepSeek with one OpenAI-compatible API

Most AI projects end up talking to more than one model provider. One model is cheaper for drafts, another is better at code, a third handles images. Every extra provider means another account, another API key, another balance to top up and another SDK quirk to learn. This post shows how to call models from several providers through one OpenAI-compatible endpoint, using APIKO AI API . The code is…

An OpenAI-compatible API can be used to call models from multiple providers through a single endpoint, simplifying the process of working with different AI models. To do this, create an API key at apiko.app, which offers pay-as-you-go billing with credit packs starting at $5, no subscription required, and no expiration on the balance.

Install the OpenAI Python SDK, set the base URL to https://api.apiko.app/v1, and provide the API key as an environment variable. Create a chat completion request using the desired model, such as gpt-6-astra, and print the model's response. Repeat the process with other models, like claude-sonnet-5-5, gemini-3.5-flash, and deepseek-v4-flash, by changing the model ID in the request.

The code remains largely the same, with only the base URL and model ID changing. This approach consolidates multiple provider accounts into one, automates routing and failover, offers automatic refunds for failed calls, and integrates seamlessly with existing OpenAI SDK tools.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Seu agente não é consistente: por que uma única execução não prova que ele funciona

O mesmo agente, o mesmo modelo, o mesmo prompt e o mesmo ambiente. Rode de novo. O resultado muda. O paper Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models…

  • Identical runs of same agent-model-prompt produced different results
  • Variation between identical runs > difference between different combinations
  • Tens to hundreds of runs needed to reliably order agents

How to Use AI to Compare Two Versions of the Same Real Estate Feasibility Model Published

Comparing two versions of a real estate feasibility model sounds like a different problem. It's mostly an interpretation problem. Excel can tell you that 214 cells changed.

  • AI can interpret complex model changes beyond simple cell diffs
  • Classify changes into inputs, formulas, hard-coded values, and value changes
  • AI explanation helps identify root causes of output metric shifts

More from Tuesday 13 October →