Google Gemini API free tier

What Google Gemini API's free tier allows

Rate limits apply per project, not per API key, and depend on the project's usage tier; the Free tier is the entry tier and moving up requires enabling billing. Google publishes the tier structure but directs you to AI Studio for the exact RPM, TPM and RPD active on your project, so no single free-tier number can be quoted here.

Published limits

Set by project tier

Free access type

Provider free tier

Credit card

Not required

Protocol

OpenAI-compatible at https://generativelanguage.googleapis.com/v1beta/openai/

Lifecycle

Active

Sources reviewed

2026-07-25

New projects start on the Free tier. Only selected models carry free-tier usage, and per-model limits are visible in AI Studio.

Where Google Gemini API sits in this catalog

Google Gemini API is one of 15 provider free tier entries among the 25 providers detailed here. It asks for no credit card, which is true of 23 of the 25. It publishes no fixed request count, as 16 of the 25 do not.

Models Google Gemini API lists as free

• Free-tier eligibility varies by model — not part of any family this catalog tracks across providers
• gemini-2.5-flash — not part of any family this catalog tracks across providers
• gemini-2.5-flash-lite — not part of any family this catalog tracks across providers

The models above do not fall into any of the multi-provider families this catalog tracks, so Google Gemini API is the only route to them here.

Checking a Google Gemini API key

The CORS preflight echoes the requesting origin and allows an Authorization header, so a browser can call this endpoint directly. That was measured against https://generativelanguage.googleapis.com on 2026-07-25.

So a key can be checked in the browser checker without installing anything. If you would rather not paste a key into a web page, this does the same thing:

#!/usr/bin/env sh
set -eu

: "${GEMINI_API_KEY:?Set GEMINI_API_KEY to a key you created yourself at the provider console}"

# Prints the models this key can reach, then the HTTP status on its own line so
# 200, 401, and 429 stay distinguishable.
curl --silent --show-error \
  --write-out '\nHTTP %{http_code}\n' \
  --header "Authorization: Bearer $GEMINI_API_KEY" \
  'https://generativelanguage.googleapis.com/v1beta/openai/models'

Using a Google Gemini API key

Google Gemini API serves the OpenAI chat completions protocol at https://generativelanguage.googleapis.com/v1beta/openai/. Point any client that accepts a custom base URL at it, and let the client read the key from GEMINI_API_KEY so the value never lands in a config file:

# Merge this snippet into ~/.codex/config.toml.
# Project-level config cannot select a custom model provider.
model = "gemini-2.5-flash"
model_provider = "gemini"

[model_providers.gemini]
name = "Google Gemini API OpenAI-compatible gateway"
base_url = "https://generativelanguage.googleapis.com/v1beta/openai"
env_key = "GEMINI_API_KEY"
wire_api = "responses"

Questions about the Google Gemini API free tier

Does Google Gemini API ask for a credit card?

No. Google Gemini API is one of 23 providers here that hand out free access without a card, so the only cost of trying it is the signup.

What are Google Gemini API's free-tier rate limits?

Google Gemini API publishes no single free-tier number: its limits are set by project tier. This catalog leaves that blank rather than guessing a figure.

What happens when a Google Gemini API key hits the limit?

The endpoint answers 429. That is a statement about the request that was refused, not about how much quota is left; only a reset header from the provider tells you when it clears.

Is the Google Gemini API free tier going away?

Nothing in Google Gemini API's own documentation says so as of 2026-07-25. New projects start on the Free tier. Only selected models carry free-tier usage, and per-model limits are visible in AI Studio.

Can Google Gemini API be used with Codex, Cline, or Continue?

Yes. Google Gemini API serves the OpenAI chat completions protocol at https://generativelanguage.googleapis.com/v1beta/openai/, so any client that accepts a custom base URL can use it. Claude Code is the exception, because it speaks the Anthropic protocol instead.

Official sources

• Gemini API rate limitshttps://ai.google.dev/gemini-api/docs/rate-limits
• Gemini API billinghttps://ai.google.dev/gemini-api/docs/billing
• Gemini OpenAI compatibilityhttps://ai.google.dev/gemini-api/docs/openai

Every figure above was read from those pages on 2026-07-25. Where a provider states a limit only inside a console, this catalog records that fact instead of a number. See the methodology for how an entry gets in and how it gets corrected.