Gemini API free tier: limits, keys and failover

What is free on Gemini

The free tier gives limited access to certain models with free input and output tokens, including Gemini Flash and Flash-Lite versions and Gemma 4. Other models are not available on it. An active project qualifies; linking a billing account moves the project to Tier 1.

Examples listed as free when we checked: gemini-3.8-flash , gemini-3.7-flash , gemini-3.5-flash , gemini-3.5-flash-lite , gemini-2.5-flash . Check the current catalog and your account access. Ficelle refreshes catalog data and applies eligibility checks during selection.

Listed free model examples on Gemini

• Gemma 4 gemma-4-31b-it
• Gemini 3.8 Flash gemini-3.8-flash

Gemini free-tier limits

Google does not publish free-tier numbers: your active limits are shown per project in AI Studio. Limits apply per project, not per key, and cover requests per minute, input tokens per minute and requests per day, which reset at midnight Pacific time. They are tighter for experimental and preview models, and Google says specified limits are not guaranteed.

Get a Gemini API key

Sign in with a Google account and accept the terms; AI Studio creates a default project and key. You must be 18 or older and in a supported country or territory. No billing account is needed for the free tier.

https://aistudio.google.com/apikey

OpenAI compatibility

Google documents Gemini as usable from the OpenAI libraries and REST by changing the key, base URL and model.

https://generativelanguage.googleapis.com/v1beta/openai/

Data and privacy

Free-tier content is used by Google to provide, improve and develop its products and machine-learning technologies, and human reviewers may read it. Google asks you not to send sensitive, confidential or personal information on the free tier. For users in the EEA, Switzerland or the UK, the paid-service data terms apply to unpaid quota too.

Through Ficelle, your Gemini key stays on your machine and prompts go straight to Gemini: there is no Ficelle proxy in between.

Before you rely on it

• Creating another key in the same project does not give you a separate quota. Check the project and model in AI Studio, then the Pacific-time daily reset.
• Free-tier prompts may be used to improve Google products and seen by human reviewers.
• Apps offered to users in the EEA, Switzerland or the UK must use paid services, per the terms.
• Free-tier limits are unpublished and visible only per project in AI Studio.
• Some models are paid-only, and Google Search grounding is not available on the free tier for Gemini 3.x Flash.

Use Gemini with automatic failover

Ficelle can include Gemini behind your local OpenAI-compatible endpoint when the integration is enabled and its models pass free-access and capability checks. Gemini is listed in Ficelle Pro's maintained provider pack. Check your installed configuration, credentials and account entitlement before relying on it. Another eligible candidate must be available for failover to succeed. Local routing guards do not control upstream billing when an account permits paid usage beyond its free allocation. See strict-zero routing and account limits.

# Gemini ships in Ficelle Pro's maintained provider pack.
ficelle doctor --text          # check this install before configuring provider access

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:8646/v1", api_key="ficelle-local")

# Ficelle selects among configured, enabled, eligible models.
# If none can serve the request, it returns an error.
client.chat.completions.create(
    model="ficelle/auto-tools",
    messages=[{"role": "user", "content": "..."}],
)

See what Ficelle Pro includes →

Pick a model type

Choose a model type for your request. Eligibility depends on the installed provider configuration, catalog data, free-access evidence and capability checks. A catalog listing alone does not confirm that your account can call a model.

• Tool calling
• JSON & structured output
• Fast, low-latency
• Reasoning
• Coding assistants
• Agent orchestration
• Long context
• Context compression
• Vision
• Audio input
• Video input
• Multimodal

Questions