Short answer: The Google Gemini API documentation cited here does not list a callable model named Gemini 3.0 Pro. The similarly named Gemini 3 Pro Preview used the ID gemini-3-pro-preview, but Google says it was shut down on March 9, 2026. The Gemini API documents Gemini 3.1 Pro Preview with the callable model ID gemini-3.1-pro-preview. That is a different, preview model—not a confirmed production-stable replacement for “Gemini 3.0 Pro.” (Gemini 3 Pro Preview, Gemini 3.1 Pro Preview)
Which Gemini Pro model can you call?
| Name | Gemini API status | Model ID | What it means |
|---|---|---|---|
| Gemini 3.0 Pro | Not listed as a callable model in the Gemini API documentation cited here | — | Don’t assume this exact name works in an API request. |
| Gemini 3 Pro Preview | Shut down March 9, 2026 | gemini-3-pro-preview |
This was an API model ID, but Google marks it shut down. |
| Gemini 3.1 Pro Preview | Listed in the Gemini API docs as a preview model | gemini-3.1-pro-preview |
This is the exact ID documented for Gemini 3.1 Pro Preview. Availability for your project still needs checking. |
| Gemini 3 Pro Image | A separately named image model in Google’s Cloud model catalog | Not the text Pro model above | Don’t confuse an image-generation listing with a text-generation API model. |
These names are not interchangeable. Google’s Gemini API page gives the shutdown date for Gemini 3 Pro Preview; its separate model page identifies gemini-3.1-pro-preview as the Gemini 3.1 Pro Preview model code. The Google Cloud catalog lists Gemini 3 Pro Image separately from its text Pro entries. (Gemini 3 Pro Preview, Gemini 3.1 Pro Preview, Google Cloud model catalog)
Make a first Gemini 3.1 Pro Preview API request
This example uses Google’s Gemini API REST generateContent route. It calls gemini-3.1-pro-preview—not a model called “Gemini 3.0 Pro.” Google’s text-generation guide documents the REST request pattern and x-goog-api-key header; the model page provides the 3.1 Pro Preview ID. (Text generation guide, Gemini 3.1 Pro Preview)
Prerequisites
- A Gemini API key associated with a Google project. In Google AI Studio, a new user gets a default project and API key after accepting the Terms of Service. If you already have a Google Cloud project, import it from Dashboard → Projects, then create a key for that project from the API Keys page. (Gemini API key guide)
curland permission to use the Gemini API with this model.- Access caveat: The documentation cited here identifies Gemini 3.1 Pro as a preview model, but does not establish whether this request requires paid billing or particular geographic eligibility. Check your project’s access and the current model documentation before relying on the model; having a key alone does not confirm model access. (Gemini 3.1 Pro Preview)
Set the key as an environment variable rather than placing the secret in source code:
export GEMINI_API_KEY="YOUR_API_KEY"
Then send a small test prompt:
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.1-pro-preview:generateContent" \\
-H "x-goog-api-key: $GEMINI_API_KEY" \\
-H "Content-Type: application/json" \\
-X POST \\
-d '{
"contents": [
{
"parts": [
{ "text": "Explain what an API is in one sentence." }
]
}
]
}'
Where to find the generated text: In a standard text response, inspect candidates[0].content.parts[0].text. A response can contain multiple candidates or parts, so handle those cases if your application needs more than this minimal example. (Text generation guide)
If the request fails, check that the model ID is spelled exactly as documented, that the key is present and permitted, and that the model is available to your project. Don’t try the old gemini-3-pro-preview ID as a workaround: Google marks that model shut down. (Gemini 3.1 Pro Preview, Gemini 3 Pro Preview)
API key security note
Google’s key documentation says that, starting May 28, 2026, new keys created in Google AI Studio are authorization keys by default, and the Gemini API rejects unrestricted standard API keys. Follow the restrictions and key-handling guidance for your key type; don’t expose a secret key in a browser app, repository, or log. (Gemini API key guide)
Is Gemini 3.1 Pro Preview a production choice?
The Gemini API documentation labels gemini-3.1-pro-preview as Preview. Its model page lists a 1,048,576-token input limit and a 65,536-token output limit. Those are model-page specifications, not a production guarantee or confirmation of access for every project. Check the current model documentation and your project’s access before adopting it. (Gemini 3.1 Pro Preview)
For a prototype or evaluation, this is the documented preview API route discussed here. For a production dependency, treat preview status as a material consideration: validate the features and access your workload requires, and confirm the current lifecycle and limits before committing. This is a planning recommendation based on the preview label, not a claim that the model cannot be used in production.
If considering Gemini 2.5 Pro instead, confirm its current Gemini API eligibility and lifecycle in the official documentation for that API channel. Status shown in another Google product or catalog should not be assumed to describe Gemini API access. (Gemini 2.5 Pro)
Bottom line
The cited Gemini API documentation does not provide a callable model ID named gemini-3.0-pro. The old gemini-3-pro-preview endpoint is shut down. The documented Pro-family option covered here is gemini-3.1-pro-preview, accessed through the Gemini API, with preview-status caveats. Use that exact identifier only if it fits your access and stability requirements—and don’t describe it as Gemini 3.0 Pro. (Gemini 3 Pro Preview, Gemini 3.1 Pro Preview)
Sources
Gemini 3.1 Pro preview | Gemini API | Google AI for Developers
Gemini 3 Pro preview | Gemini API | Google AI for Developers
Text generation - generateContent API | Google AI for Developers
Using Gemini API keys - generateContent API | Google AI for Developers