Gemini Embeddings Free Tier Quota Stuck at 0 After Overage – No Reset Across Projects

Gemini API
,
1

Hi everyone,

I’m encountering a persistent “quota exceeded” error (429 RESOURCE_EXHAUSTED) with the Gemini Embeddings API on the free tier, even though I haven’t used it for over a week. The error message shows all relevant quotas set to a limit of 0 (per day/minute, per user/project/model), which doesn’t match the documented free tier limits (e.g., 1,000 RPD, 100 RPM).

Background:

  • I was testing a tutorial and accidentally exceeded the daily limit (about double the 1,000 RPD) on one day.

  • Since then, all attempts to make even a single minimal request fail with the same error.

  • I’ve waited a full week for reset, but no change.

  • Created a brand new Google Cloud project with a fresh API key – same issue.

  • Tried both legacy “embedding-001” and stable “gemini-embedding-001” models.

  • Quota dashboard in Cloud Console shows 0% usage but limits as 0.

  • No billing account linked yet (staying on free tier), and I’m in an eligible region (Austria).

Error Details (from cURL/Python test with “Hello world” text):

text

{
  "error": {
    "code": 429,
    "message": "You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits.\n* Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0\n* Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0\n* Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0\n* Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0",
    "status": "RESOURCE_EXHAUSTED",
    "details": [
      {
        "@type": "type.googleapis.com/google.rpc.QuotaFailure",
        "violations": [
          {
            "quotaMetric": "generativelanguage.googleapis.com/embed_content_free_tier_requests",
            "quotaId": "EmbedContentRequestsPerDayPerUserPerProjectPerModel-FreeTier"
          },
          {
            "quotaMetric": "generativelanguage.googleapis.com/embed_content_free_tier_requests",
            "quotaId": "EmbedContentRequestsPerMinutePerUserPerProjectPerModel-FreeTier"
          },
          {
            "quotaMetric": "generativelanguage.googleapis.com/embed_content_free_tier_requests",
            "quotaId": "EmbedContentRequestsPerMinutePerProjectPerModel-FreeTier"
          },
          {
            "quotaMetric": "generativelanguage.googleapis.com/embed_content_free_tier_requests",
            "quotaId": "EmbedContentRequestsPerDayPerProjectPerModel-FreeTier"
          }
        ]
      },
      {
        "@type": "type.googleapis.com/google.rpc.Help",
        "links": [
          {
            "description": "Learn more about Gemini API quotas",
            "url": "https://ai.google.dev/gemini-api/docs/rate-limits"
          }
        ]
      }
    ]
  }
}

Has anyone else run into this after an overage? Is this a bug where the free tier gets “stuck” or flagged? Enabling billing for Tier 1 is an option, but I’d prefer to resolve on free tier if possible. Any advice on forcing a reset or escalating?

Thanks!

1 Like
3

I’m facing the same error, even thought this is my first time attempting to use the API. I’m wondering if it is a bug

4

Hi @Ahmed_Djalal @Piotr_Gruszka,

The recent issues affecting AI studio and Gemini API have been resolved, and all systems are operational again. We apologize for the inconvenience and disruption this may have caused to your applications and workflows. Please let us know if you continue to face any issues.

1 Like
5

Thanks for acknowledging the issue, Krish.
Im still experiencing issues with quota: “EmbedContentRequestsPerMinutePerUserPerProjectPerModel-FreeTier“

Both in the Dashboard (with a value of 0), and in the API (with a 429 error).

6

Hi @Santiago,

Welcome to the Google AI Forum! :confetti_ball: :confetti_ball:

Please try again after few hours and let me know if you are still facing the issue.

7

Hi, Krish. I’m still seeing the same error one day later.
Im moving on to a different model, but let me know if you need additional information (in case other developers are facing the same issue).

9

Same here. Stuck at 0 since my first request yesterday.

12

I am having a similar issue with the genai SDK embed_content with a free tier API key.

The genai SDK uses the batch embedding API behind the scenes, which for API keys using the free tier now appears to return “Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0”

Possible workaround is to use the requests library to call the API directly instead of genai.embed_content()

import requests, os

def test_gemini_embedding():
    api_key = os.getenv("GEMINI_API_KEY")
    url = "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:embedContent"
    headers = {"x-goog-api-key": api_key, "Content-Type": "application/json"}
    data = {"model": "models/text-embedding-004", "content": {"parts":[{"text": "What is the meaning of life?"}]}}
    response = requests.post(url, headers=headers, json=data)
    return response

test_response = test_gemini_embedding()
print(f"Status: {test_response.status_code}")

That works for me with my free tier API key.

2 Likes
13

mhm, after sending 100 items × 768 floats the embeddings are exhausted, does not really work. google console does not show any use..
I will just use local embeddings for now…

15

Hi,

I’m encountering the same error when using the Generative Language / Gemini API:

Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0

It seems that my quota for that metric is set to 0, even though the documentation mentions a free tier.

Could you please help clarify:

Is there indeed a Free Tier for embed_content (or embedding) requests?

Why is my quota for that metric 0 — is this a default, a misconfiguration, or a limitation in my region/project?

If there is a free tier, how can I enable or request it (or increase it)?

My project Project ID is : gen-lang-client-0328127297

Thanks in advance for your help.

PS:
If quota doesn’t work for gemini-embedding-001 looks like it’s working for the text-embedding-004