vMira

What is OpenAI-compatible API?

An OpenAI-compatible API exposes endpoints and request/response shapes that match OpenAI's REST API (chat/completions, embeddings, models). Pointing the OpenAI SDK at the alternative provider's base URL with a new API key works without code changes.

Also known as: OpenAI-compatible REST API, drop-in OpenAI replacement

Why compatibility matters

OpenAI's API became the de facto standard for chat-completion endpoints. Most LLM tooling, frameworks (LangChain, LlamaIndex), and customer code is written against the OpenAI request shape. By exposing the same shape, a provider lets developers migrate in minutes instead of rewriting integrations. This is the difference between a vendor switch costing an afternoon versus a sprint.

What "compatible" usually covers

At minimum: POST /v1/chat/completions accepting messages, model, temperature, max_tokens, stream, and returning choices with message.content. Most providers also implement /v1/models (list available models), /v1/embeddings (vectorize text), and increasingly /v1/responses (the newer agentic shape). Tool use, function calling, and structured outputs vary in fidelity across providers — verify before depending on advanced features.

How to migrate

With the openai Python or JavaScript SDK, change two lines: the base_url to the new provider's endpoint, and the API key. The rest of your code — message construction, streaming handlers, retry logic — stays the same. For vMira: base_url="https://api.vmira.ai/v1", api_key="YOUR_VMIRA_KEY", and use the model IDs documented at docs.vmira.ai (see the pricing page for current rates).

Limits of compatibility

OpenAI-compatible doesn't mean OpenAI-identical. Token tokenizers differ (so cost estimates need recalibration), context windows differ, model-specific features (vision, audio, agentic tools) may have different shapes or not exist. Always run a smoke test against your actual prompts before swapping in production.

Last updated · First published

Related terms

Large language model (LLM)

A large language model is a neural network trained on a massive corpus of text to predict the next token given the previous ones. Modern LLMs have billions to trillions of parameters and can generate coherent prose, answer questions, write code, and perform reasoning tasks well beyond simple text completion.

Embedding

An embedding is a fixed-length vector of floating-point numbers that represents the semantic meaning of a piece of text (or image, audio, etc.). Two embeddings are similar (small cosine distance) when their source texts are semantically similar — even if the words differ.

Tool use

Tool use is the LLM capability where, instead of producing a normal text response, the model emits a structured request to invoke an external function or API. The host application executes the function, returns the result to the model, and the model continues the conversation using that result.

AI agent

An AI agent is an LLM-driven system that can take multiple actions toward a goal — invoking tools, reading results, deciding next steps, and iterating — rather than producing a single chat response. The defining feature is autonomy: the agent decides what to do next based on what it has seen so far.

Try OpenAI-compatible API in vMira

Open the workspace and explore — no credit card required.

Open vMira