Historical guide to Google’s retired Gemini 3 Pro Preview API, with specifications, migration checks, and the Gemini 3.1 Pro replacement.
At a glance
API model ID: gemini-3-pro-preview
Capabilities & boundaries
Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.
The historical model supported low and high, with high as the default. Do not carry that two-level configuration into a replacement without reviewing its documentation. These controls were relative thinking levels, not a strict token budget.
Put it to work
Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.
Workflow 01
Turn archived examples into a repeatable acceptance set.
From these archived prompts and reviewed outputs, design a migration evaluation for an available replacement model. Group cases by required behavior, define a scoring rubric, and include edge cases for citations, formatting, and tool selection. Flag expectations that depend on retired features. Do not fabricate benchmark scores or call the old endpoint.
Workflow 02
Use saved results to identify changes that matter.
Compare the two saved answers and their source packet below. Identify factual differences, citation errors, omitted constraints, and formatting changes. Score only what the evidence supports and explain each deduction. Separate model-quality differences from different input settings. End with the cases that need a fresh human-reviewed test.
Workflow 03
Locate assumptions that need review before switching models.
Review the supplied integration configuration for assumptions tied to gemini-3-pro-preview. List the model ID, thinking settings, tools, schemas, and token limits that need checking against the replacement documentation. Propose a minimal migration checklist with rollback criteria. Do not invent unsupported settings or execute the migration.
Developer reference
Google API reference pricing is not EZ Ai Assist subscription prices.
View EZ Ai Assist plansHistorical API pricing was not verified from the reviewed official sources. Google’s current pricing table no longer lists the original retired model, so no numeric rates are shown here.
Common questions
The original Gemini 3 Pro model retired March 9, 2026. Google’s release notes say gemini-3-pro-preview now points to gemini-3.1-pro-preview, so the old ID is not continued access to the original model. Prefer the explicit replacement ID and verify current routing and behavior before use.
Google’s lifecycle table recommends gemini-3.1-pro-preview. Follow the linked Gemini 3.1 Pro guide, then test your prompts and tools. Model replacement is not proof of identical outputs, defaults, latency, or cost.
The reviewed current official pricing page no longer lists the original retired model, and its historical rates were not verified. Showing the replacement’s rates or a zero value as Gemini 3 Pro pricing would be misleading.
It preserves a useful reference for people following older links or migrating an existing workflow. The lifecycle notice and replacement link explain what changed without silently redirecting to a different model.
Yes—adapt these original editorial examples to the inputs and controls available in your workspace. Share only material you are authorized to provide. They are starting points, not benchmarks or a promise of a particular result.
No. The 1,048,576-token input limit is capacity, not a recall guarantee. Organize sources with names and sections, request citations, and check them. The separate maximum output is 65,536 tokens; actual requests must also fit integration limits.
No. Provider API token pricing and EZ Ai Assist subscriptions are separate. This historical guide does not show unverified numeric API rates. Use our pricing page for current plans and check the app for enabled models and controls.
Check the source
Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.
Same provider
Google’s Gemini 3.8 Flash supports multimodal understanding, three thinking levels, and tool-assisted workflows with promotional API pricing.
Google’s Gemini 3.7 Flash combines multimodal inputs, configurable thinking, and structured tool workflows for repeatable everyday tasks.
Google’s Gemini 3.1 Pro Preview supports complex synthesis, coding, and multimodal analysis with a 1M-token input limit.
Google’s Gemini 3.1 Pro Preview variant favors custom tools over bash; evaluate tool selection and answer quality for your workflow.