Google Gemini through Squiid
Gemini models with very long context, video and audio input. Google Gemini is live on Squiid today.
What Google Gemini is
Google's Gemini API serves the Gemini model family through the Google AI developer platform. Its distinguishing features are context length, native multimodality and grounding: you can pass a long PDF, an audio file or a video directly in a request, use the Files API to reuse large inputs, and enable grounding with Google Search so answers cite current pages. Function calling and JSON schema responses work the same way they do on other providers, so swapping Gemini in behind an existing abstraction is usually mechanical. Gemini Flash models are positioned as the cheap high-throughput tier, while the Pro models take the harder reasoning work, and both are reachable from the same client.
For an app built with an agent, Gemini tends to be the model reached for when the input is big or is not text. Summarising a recorded sales call, reading a 300 page compliance document, pulling line items out of a scanned invoice, or captioning user-uploaded video all fit it well. It also shows up as the cheap high-volume tier for classification when latency and price matter more than the last few points of quality.
Why connect it through Squiid
Squiid holds the Google API key and routes requests to https://api.squiid.io/v1/google-gemini/... with Authorization: Bearer $SQUIID_API_KEY, and the Google GenAI SDKs work by pointing their base URL at the gateway (gateway convention). You do not create a Google Cloud project, attach a billing account or manage a service account JSON file to get started. Token and media usage is metered against prepaid credits at Google's listed rates, capped by your balance, and billed on the single Squiid invoice alongside everything else the project uses. Because provisioning is instant, an agent can add Gemini to a project in the same session it decides it needs long-context summarisation.
- One account, one key, one bill, one dashboard. Google Gemini sits beside every other service your project uses, on the same invoice and the same credit balance.
- Key custody. Squiid holds the Google Gemini credentials. Your code carries
SQUIID_API_KEY, so GEMINI_API_KEY, GOOGLE_API_KEY, GOOGLE_GENAI_BASE_URL 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 Google Gemini 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
- Gemini text, vision and long-context models
- Audio, video and PDF input through the same key
- No Google Cloud project or service account file to set up
- Per-model usage metering in the Squiid dashboard
- Google list pricing with no Squiid markup
How to connect Google Gemini
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 GEMINI_API_KEY, GOOGLE_API_KEY, GOOGLE_GENAI_BASE_URL
SQUIID_API_KEY=sq_live_xxxxxxxxxxxxxxxxxxxxxxxx
# every request: https://api.squiid.io/v1/google-gemini/...
# header: Authorization: Bearer $SQUIID_API_KEY
Add it in your dashboard
Open the Squiid catalog, add Google Gemini 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 GEMINI_API_KEY, GOOGLE_API_KEY, GOOGLE_GENAI_BASE_URL. Nothing else from Google Gemini 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/google-gemini/. Gemini CLI and Cursor generally use the Google GenAI SDK with the key from the environment, often with the Files API for anything larger than a single prompt.
Pricing through Squiid
Google charges per input and output token by model, with separate rates for audio and video input, at the provider's listed price. Squiid passes that through at par: one dollar of prepaid credit is one dollar of Google Gemini usage, with no markup and no per-request margin.
Google Gemini 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 Google Gemini 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: Google Gemini is usage-metered, so leaving means creating your own Google Gemini key and pointing the client at it. Squiid never owns your code, your schema or your domain, and the gateway speaks Google Gemini'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
Google Gemini 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 Google Gemini 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
OpenAI
LLM APIsGPT models, embeddings, images and realtime voice over one API
LiveInstantAnthropic
LLM APIsClaude models for long-context reasoning, coding and tool use
LiveInstantGoogle Cloud
CloudsGoogle Cloud services including Vertex AI through the partner program
RoadmapPartnerDeepgram
Voice and media AIFast, accurate speech to text with live streaming transcription
Next upInstant MUMux
Storage and mediaVideo infrastructure with adaptive streaming, playback data and a player
RoadmapProvisionedQuestions people ask
Can Gemini CLI use Gemini through Squiid?
Yes. Gemini CLI and any Google GenAI SDK point at the Squiid gateway base URL and send SQUIID_API_KEY, so the Google key stays in Squiid's custody.
Do I need a Google Cloud billing account?
No. Squiid provisions Gemini API access for you, so there is no Google Cloud project, billing account or service account key to create.
Is Vertex AI the same as the Gemini API?
No. Vertex AI is the Google Cloud enterprise surface for the same models. Squiid connects the Gemini developer API here, and Google Cloud is listed separately as a partner service.
Does Squiid add a fee to Gemini tokens?
No. Gemini usage is billed at Google's list price against your credits. Squiid's revenue is the plan fee and the top-up percentage, not a per-token margin.
Can I send video and audio through the gateway?
Yes. Multimodal requests pass through unchanged, and the media portion of the usage is metered at Google's published rate for that input type.
Connect Google Gemini with one key.
The Gemini API gives you Google's multimodal models, with context windows measured in the millions of tokens and native video, audio and PDF input. Metered per token through Squiid at Google's list price.