---
title: "OpenAI | Skills We Assign For | Azendo"
description: "Building on OpenAI models — capability, cost, and avoiding provider lock-in, plus the Azendo roles assigned for it."
url: "https://azendo.co/skills/openai/"
---

[Skills](https://azendo.co/skills/) AI and machine learning 

# OpenAI.

OpenAI provides frontier language and multimodal models through an API, alongside embeddings, speech and image generation. For most products it is the default first provider, reached through a single HTTP interface rather than any infrastructure.

## Where OpenAI fits on a long engagement.

The reason to start here is that the capability is available immediately and the integration is a few hours of work. For establishing whether a product idea is feasible at all, that removes every infrastructure question and leaves only the question that matters.

The costs that follow are operational rather than technical. Per-token pricing means usage growth is cost growth in a way self-hosted inference is not, rate limits shape architecture, and model deprecations force migrations on the provider's schedule rather than yours. A prompt tuned against one model version does not necessarily behave the same on the next.

## What an assigned team does with OpenAI.

The practical defence is an abstraction at the boundary. Calling a provider directly from throughout the application makes changing model or provider a large refactor; routing through one internal interface makes it a configuration change and makes comparison possible.

That is an architectural decision worth making before the first feature ships rather than after, which is the kind of judgement scoped under [ai engineering services](https://azendo.co/services/ai-engineering/).

## What we use OpenAI for.

* Establishing feasibility quickly A working prototype in days, so the product question is answered before infrastructure is chosen.
* A provider boundary from the start One internal interface, so switching model or vendor is configuration rather than a refactor.
* Cost modelled against real usage Token spend projected at expected volume, because per-token pricing scales with success.

## How OpenAI capacity is assigned.

AI capacity is agreed as a [committed monthly capacity](https://azendo.co/pricing/) across the discipline, with provider abstraction treated as a design requirement rather than a later refactor.

## Roles we assign OpenAI for

* [AI Engineer AI engineering](https://azendo.co/services/ai-engineering/ai-engineer/)

## Service lines it sits in

* [AI engineering](https://azendo.co/services/ai-engineering/)

Capacity is agreed as a committed monthly capacity across a discipline, not per skill.

## Related in ai and machine learning

* [PyTorch — skill we assign for](https://azendo.co/skills/pytorch/)
* [TensorFlow — skill we assign for](https://azendo.co/skills/tensorflow/)
* [scikit-learn — skill we assign for](https://azendo.co/skills/scikit-learn/)
* [Pandas — skill we assign for](https://azendo.co/skills/pandas/)
* [NumPy — skill we assign for](https://azendo.co/skills/numpy/)
* [embeddings — skill we assign for](https://azendo.co/skills/embeddings/)
* [function calling — skill we assign for](https://azendo.co/skills/function-calling/)
* [vLLM — skill we assign for](https://azendo.co/skills/vllm/)

## Tell us what your roadmap needs OpenAI for.

A service delivery manager replies with the disciplines we would assign, the monthly capacity and what the first month looks like.

[All skills we assign for](https://azendo.co/skills/)