OpenAI via VerticalAPI

Call GPT-4o, GPT-4 Turbo and the o1 reasoning family through a single OpenAI-compatible endpoint. Bring your own OpenAI API key — VerticalAPI adds zero markup on tokens.

Start free with your OpenAI key → Read the docs

Endpoint: https://api.verticalapi.com/v1/chat/completions · BYOK header: X-Provider-Key: sk-...

Supported models

OpenAI models routed by VerticalAPI

Pass the model ID below as model in any OpenAI-compatible request. New OpenAI models are typically supported within 24h of release.

Model ID	Name	Context	Pricing (provider)
`gpt-4o`	GPT-4o	128K	$2.50 / $10 per 1M tok (in/out)
`gpt-4o-mini`	GPT-4o mini	128K	$0.15 / $0.60 per 1M tok
`gpt-4-turbo`	GPT-4 Turbo	128K	$10 / $30 per 1M tok
`o1`	o1	200K	$15 / $60 per 1M tok — reasoning model
`o1-mini`	o1-mini	128K	$3 / $12 per 1M tok — reasoning, cheaper

Pricing reflects OpenAI's rates — you pay OpenAI directly. VerticalAPI adds zero markup on tokens.

Quickstart

5-line OpenAI call via VerticalAPI

Drop-in replacement for the OpenAI SDK. Works with the OpenAI Python client, Node, Go, curl — anything that speaks HTTP.

                openai_quickstart.py
                Python
            
from openai import OpenAI

client = OpenAI(
    base_url="https://api.verticalapi.com/v1",
    api_key="vapi_...",
    default_headers={"X-Provider-Key": "sk-..."}
)

response = client.chat.completions.create(
    model="gpt-4o",  # OpenAI
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Why use OpenAI via VerticalAPI

Four reasons developers route OpenAI through us

Zero token markup

You pay OpenAI directly with your own key. VerticalAPI's revenue is the gateway subscription, not a tax on your tokens.

One key, every provider

OpenAI alongside OpenAI, Anthropic, Gemini and 12 more — same OpenAI-compatible endpoint, same SDK, switchable per-request.

Latency & cost monitoring

Per-request token counts, p50/p95 latency and cost dashboards out of the box. Compare OpenAI to other providers on identical prompts.

Observability built in

Every OpenAI call gets a trace ID, replayable payload and audit log entry. Wire to Datadog or Sentry via OpenTelemetry.

Best for

Where OpenAI shines

agentic workflows structured output function calling multimodal vision

FAQ

Common questions about OpenAI on VerticalAPI

Do I pay OpenAI directly or VerticalAPI?

You pay OpenAI directly via your own API key. VerticalAPI adds zero markup — we make money on the gateway subscription, not on your tokens.

Are all OpenAI models supported?

Yes. GPT-4o, GPT-4 Turbo, GPT-3.5, o1, o1-mini, embeddings and the moderation endpoint all flow through. New models are typically supported within 24h of OpenAI's release.

Can I use OpenAI's structured outputs and tool calling?

Yes — request and response shape is byte-compatible with OpenAI's API. response_format, tools and tool_choice all work as documented by OpenAI.

What about rate limits?

VerticalAPI inherits your OpenAI account's rate limits. We don't add a layer on top, but you can see real-time consumption in the dashboard.

Switch providers

All supported LLM providers

Same endpoint, same SDK — just change the model and the BYOK header.

OpenAI Anthropic Google Gemini Mistral AI Meta Llama xAI Grok Groq Together AI Fireworks AI Perplexity Sonar Cohere AI21 Labs AWS Bedrock Azure OpenAI Google Vertex AI

Ship on OpenAI in 60 seconds

Free tier — bring your own OpenAI key, zero markup, OpenAI-compatible endpoint.

Get your VerticalAPI key →