Candid Tools

Gemini model IDs

Gemini Model IDs shows the exact Gemini API ID for each Gemini text model, whether it is stable or preview, and its paid price per 1M tokens, in your browser.

The two models Google points new projects to, and the ID to use:

  • The model ID for Gemini 3.8 Flash is$0.75 in / $3.75 out per 1M tokens
  • The model ID for Gemini 3.5 Flash-Lite is$0.30 in / $2.50 out per 1M tokens

11 models shown. Prices are standard API rates in USD per 1M tokens. Last checked against each provider's official docs.

  • Gemini 3.8 FlashGoogle
    Status
    Current
    Input / 1M
    $0.75
    Output / 1M
    $3.75

    Price doubles on January 1, 2027 (per Google's pricing page).

  • Gemini 3.5 Flash-LiteGoogle
    Status
    Current
    Input / 1M
    $0.30
    Output / 1M
    $2.50
  • Gemini 3.7 FlashGoogle
    Status
    Available
    Input / 1M
    $0.75
    Output / 1M
    $3.75

    Price doubles on January 1, 2027 (per Google's pricing page).

  • Gemini 3.6 FlashGoogle
    Status
    Available
    Input / 1M
    $0.75
    Output / 1M
    $3.75

    Price doubles on January 1, 2027 (per Google's pricing page).

  • Gemini 3.5 FlashGoogle
    Status
    Available
    Input / 1M
    $1.50
    Output / 1M
    $9.00
  • Gemini 3.1 Flash-LiteGoogle
    Status
    Available
    Input / 1M
    $0.25
    Output / 1M
    $1.50

    Audio input costs $0.50 per 1M tokens.

  • Gemini 3.1 Pro (preview)Google
    Status
    Preview
    Input / 1M
    $2.00
    Output / 1M
    $12.00

    Prompts over 200K tokens: $4.00 in / $18.00 out for the whole request.

  • Gemini 3 Flash (preview)Google
    Status
    Preview
    Input / 1M
    $0.50
    Output / 1M
    $3.00

    Audio input costs $1.00 per 1M tokens.

  • Gemini 2.5 ProGoogle
    Status
    Legacy
    Input / 1M
    $1.25
    Output / 1M
    $10.00

    Prompts over 200K tokens: $2.50 in / $15.00 out for the whole request. Google limits 2.5 models to past users; not deprecated.

  • Gemini 2.5 FlashGoogle
    Status
    Legacy
    Input / 1M
    $0.30
    Output / 1M
    $2.50

    Google limits 2.5 models to past users; audio input costs $1.00.

  • Gemini 2.5 Flash-LiteGoogle
    Status
    Legacy
    Input / 1M
    $0.10
    Output / 1M
    $0.40

    Google limits 2.5 models to past users; audio input costs $0.30.

At a glance

Accepts
A model name or partial ID you type
Outputs
The model ID to copy, status and paid tier price, plus CSV or PDF of the list
Where it runs
Entirely in your browser, on your device
What leaves your device
Nothing - what you type stays in this tab - the list ships with the page
Limits
A snapshot of the provider's docs, checked October 8, 2026; text models only, standard (non-batch) prices
Account
Not required - there is no sign-up
Price
Free, with no watermark and no usage cap
Made by
Visrut
Last updated
8 October 2026

Gemini model IDs are the model name in lowercase with hyphens, keeping the dot in the version: Gemini 3.5 Flash-Lite is gemini-3.5-flash-lite. A preview model adds -preview to the end. The table opens on Google's Gemini text models in the Gemini API, with stable, preview and the access-limited 2.5 models, and their paid tier price per 1M tokens.

Where the ID goes

It is the model argument in the Google GenAI SDK. This is the Python example from Google's quickstart:

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="Explain how AI works in a few words"
)
print(interaction.output_text)
From Google's Gemini API quickstart.

Stable, preview and latest

Google publishes four kinds of name. A stable ID (gemini-3.6-flash) points at a fixed model and is what Google suggests for production. A preview ID can be used in production but can be deprecated on two weeks' notice. A latest alias (gemini-flash-latest) is swapped to each new release. Experimental models are for feedback, not production. This table lists stable and preview IDs only.

Free tier versus paid tier prices

The prices shown are the paid tier. Many Gemini models also have a free tier with rate limits, where input and output tokens cost nothing, but Google's pricing page notes that free tier content is used to improve its products and paid tier content is not. Gemini 3.1 Pro preview has no free tier.

When this is and isn't the right page

Frequently asked questions

How much do 1M tokens cost on Gemini?

On the paid tier, 1M input tokens cost from $0.10 (Gemini 2.5 Flash-Lite) to $2.00 (Gemini 3.1 Pro (preview)), and output costs more: $0.40 and $12.00 per 1M on those two. Gemini 3.8 Flash is $0.75 in and $3.75 out until December 31, 2026. Output prices include thinking tokens. Prices as of October 8, 2026.

What is the model ID for Gemini 3.1 Pro?

gemini-3.1-pro-preview. Gemini 3.1 Pro is only offered as a preview, so the ID carries the -preview suffix, and Google's pricing page lists no free tier for it. The older gemini-3-pro-preview has been shut down.

Is there a Gemini ID that always points at the newest model?

Yes. Google documents latest aliases such as gemini-flash-latest, which it hot-swaps to each new release of that model line, with two weeks' email notice for breaking changes. For production Google recommends a specific stable ID such as gemini-3.6-flash instead.

Why are some Gemini prices going up in 2027?

Google's pricing page lists Gemini 3.6 Flash, 3.7 Flash and 3.8 Flash at $0.75 input and $3.75 output per 1M tokens through December 31, 2026, and $1.50 and $7.50 from January 1, 2027. The table shows today's price with a note on those rows.

Can I still use Gemini 2.5 Pro and 2.5 Flash?

Only if your project already used them. Google says the 2.5 models are not deprecated and keep being served, but access is limited to past users, and new projects should use 3.5 Flash-Lite or 3.8 Flash.