OpenAI through Squiid
GPT models, embeddings, images and realtime voice over one API. OpenAI is live on Squiid today.
What OpenAI is
OpenAI runs the GPT family and exposes it through a single HTTP API. The Responses and Chat Completions endpoints cover text generation, function calling, JSON Schema structured output and vision input, while separate endpoints handle embeddings for retrieval, image generation, speech to text and the Realtime API for low latency voice. Most teams reach it through the official openai package for Python or Node, or through frameworks like the Vercel AI SDK and LangChain that wrap the same endpoints.
In a vibe-coded app OpenAI is usually the first service added and the last one removed. It writes the product copy, classifies support tickets, extracts fields from uploaded documents, powers the chat panel and generates the embeddings that a vector database stores. Because it is called on nearly every request path, its key ends up in more places than any other credential: local .env files, CI secrets, preview deployments and whatever the agent pasted into a config file at 2am. Squiid treats it accordingly: OpenAI was the first service connected and is the one used to prove the gateway under real traffic.
Why connect it through Squiid
Squiid holds the upstream OpenAI key and issues you a single SQUIID_API_KEY. Requests go to https://api.squiid.io/v1/openai/... with an Authorization: Bearer header, and the official SDKs work by pointing their base URL at the gateway (gateway convention). Every call is metered against your prepaid credits at OpenAI's list price, shown per model in your dashboard, and stops when credits run out instead of producing an unfunded bill. You can revoke or rotate the Squiid key without touching the upstream account, and OpenAI usage lands on the same monthly invoice as your database, email and hosting. If a contractor needs access for a week, you issue and expire a Squiid key instead of sharing the OpenAI credential.
- One account, one key, one bill, one dashboard. OpenAI sits beside every other service your project uses, on the same invoice and the same credit balance.
- Key custody. Squiid holds the OpenAI credentials. Your code carries
SQUIID_API_KEY, so OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_ORG_ID never land in a repository, a preview deployment or an agent’s context. - Metering you can see. Every call is counted per service and per day, so you know what OpenAI costs before the month ends.
- Pause on zero. When prepaid credits run out the gateway stops authorizing usage instead of running up a bill you did not fund.
- One rotation. Rotating the Squiid key cuts off every agent, worker and deployment at once, with no provider key to hunt down.
What you get
- GPT chat, reasoning and vision models through the gateway
- Embeddings, image generation and speech endpoints on the same key
- Per-model token spend in the Squiid dashboard
- Official SDK compatibility by base URL swap
- No markup: $1 of credit is $1 of OpenAI usage
How to connect OpenAI
One variable replaces the provider credentials this service would normally need. Requests go to the gateway and the official SDKs work by pointing their base URL at it (gateway convention).
# .env
# replaces OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_ORG_ID
SQUIID_API_KEY=sq_live_xxxxxxxxxxxxxxxxxxxxxxxx
# every request: https://api.squiid.io/v1/openai/...
# header: Authorization: Bearer $SQUIID_API_KEY
Add it in your dashboard
Open the Squiid catalog, add OpenAI and fund credits. Access is instant and metered per request.
Put the one key in your env
Add SQUIID_API_KEY to .env and delete OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_ORG_ID. Nothing else from OpenAI needs to exist in your project.
Point your agent at it
Claude Code, Cursor and Codex read the same variable and call https://api.squiid.io/v1/openai/. Claude Code and Cursor typically add the OpenAI SDK, read the key from the environment and call it from a server route or an edge function rather than the browser.
Pricing through Squiid
OpenAI charges per input and output token, with different rates per model, at the provider's listed price. Squiid passes that through at par: one dollar of prepaid credit is one dollar of OpenAI usage, with no markup and no per-request margin.
OpenAI has no subscription attached on Squiid today. If a plan is required for a feature you need, it passes through at the provider’s listed price with no Squiid fee.
Squiid adds no markup to provider prices. There is a free plan at $0 a month with a 15% fee when you top up credits, Solo at $19.97 a month with a top-up fee that starts at 8% and falls to 3.5% as your spend grows, Team from $29.97 a seat a month with the same ladder one point lower, and Custom with a rate of 3% or less. Credits are prepaid, so OpenAI usage stops when the balance reaches zero rather than producing an invoice you did not fund. Auto top-up with a cap keeps production running without handing anyone an open-ended card.
If you leave
Nothing to move: OpenAI is usage-metered, so leaving means creating your own OpenAI key and pointing the client at it. Squiid never owns your code, your schema or your domain, and the gateway speaks OpenAI's own API, so the client change is a base URL. The handover page lists what happens for every provider in the catalogue.
Works with every coding agent
OpenAI through Squiid is just an HTTP call with a bearer token, so every agentic coding tool can use it with the single key already in your environment:
- Claude Code
- Cursor
- ChatGPT
- Codex
- Grok
- Gemini CLI
- GitHub Copilot
- Windsurf
- Perplexity
- Devin
- Replit
- v0
- Lovable
- Cline
Vibe coding a feature on OpenAI usually means asking for it in plain language and letting the agent write the integration. Because the key is Squiid’s rather than the provider’s, it can do that without ever holding a credential that could be leaked, logged or committed.
Related services
Anthropic
LLM APIsClaude models for long-context reasoning, coding and tool use
LiveInstantGoogle Gemini
LLM APIsGemini models with very long context, video and audio input
LiveInstant GRGroq
LLM APIsVery fast inference for open models on custom LPU hardware
Next upInstant PIPinecone
Vector and searchManaged vector database for retrieval augmented generation at scale
Next upProvisionedSupabase
DatabasesPostgres with auth, storage, realtime and edge functions attached
Next upProvisionedQuestions people ask
Is OpenAI live on Squiid right now?
Yes. OpenAI is the first service marked live in the Squiid catalog, so you can add it, fund credits and start making calls immediately.
Can Claude Code use OpenAI through Squiid?
Yes. Claude Code reads SQUIID_API_KEY from your .env and points the OpenAI SDK base URL at the Squiid gateway, so no OpenAI key ever reaches your repository.
Does Squiid mark up OpenAI token prices?
No. Credits are spent at OpenAI's list price, dollar for dollar. Squiid earns from the plan fee and the percentage taken when you top up credits, never from a per-token margin.
Which OpenAI models can I call through the gateway?
The models available on your OpenAI account through the standard API, including the GPT chat and reasoning models, embedding models and image models. New models appear as OpenAI ships them.
What happens if my credits run out mid-request?
The gateway stops authorizing new OpenAI calls and returns an error your app can handle, rather than letting spend continue. Auto top-up with a cap keeps this from happening in production.
Connect OpenAI with one key.
OpenAI's API serves the GPT model family for chat, reasoning, tool calling and structured output, plus embeddings, image generation and realtime audio. It is live on Squiid today and billed per token with no markup.