# Persistent High Latency with \`gemini-2.5-pro\`

**URL:** <https://discuss.ai.google.dev/t/persistent-high-latency-with-gemini-2-5-pro/92047>\
**Category:** Gemini API\
**Tags:** generative-ai, gemini-2-5\
**Created:** [July 2, 2025, 9:03am UTC](https://discuss.ai.google.dev/t/persistent-high-latency-with-gemini-2-5-pro/92047 "2025-07-02T09:03:16Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![Khachik\_Smbatyan](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/khachik_smbatyan/32/57532_2.png) [@Khachik\_Smbatyan](https://discuss.ai.google.dev/u/Khachik_Smbatyan)\
**Post date:** [July 2, 2025, 9:03am UTC](https://discuss.ai.google.dev/t/persistent-high-latency-with-gemini-2-5-pro/92047/1 "2025-07-02T09:03:16Z")

</div>

We are experiencing significant latency issues with the `gemini-2.5-pro` model when using the `generate_content` endpoint.

**Configuration:**

```python
genai_config = {
    'automatic_function_calling': {'disable': True},
    'tool_config': {'function_calling_config': {'mode': 'auto'}},
    'thinking_config': {'thinking_budget': -1, 'include_thoughts': True}
}

```

**Example Call:**

```python
response = await client.aio.models.generate_content(
    model="gemini-2.5-pro",
    config=genai_config,
    contents=messages
)

```

**Observed Latency:**

- Request duration: ~7 minutes

- Usage metadata:

**Dashboard Metrics:**

- Average latency: ~35 seconds
- 99th percentile latency: 8 minutes

These latency issues have persisted for the past 3–4 days and are affecting nearly all requests at the tail end. Is this a known issue, and is any mitigation currently underway? Has anyone else observed similar behavior?

---

<div class="post-metadata">

**Author:** ![Krish\_Varnakavi1](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/krish_varnakavi1/32/56962_2.png) [@Krish\_Varnakavi1](https://discuss.ai.google.dev/u/Krish_Varnakavi1)\
**Post date:** [July 3, 2025, 2:24am UTC](https://discuss.ai.google.dev/t/persistent-high-latency-with-gemini-2-5-pro/92047/3 "2025-07-03T02:24:46Z")

</div>

Hi @Khachik_Smbatyan,

Thanks for providing your configuration settings and yes, I have observed the same as well.. I will try to find out the root cause of this problem and try to resolve it soon..

In the meanwhile, please try again in few days and let me know if you are still observing such latencies.

---

<div class="post-metadata">

**Author:** ![Khachik\_Smbatyan](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/khachik_smbatyan/32/57532_2.png) [@Khachik\_Smbatyan](https://discuss.ai.google.dev/u/Khachik_Smbatyan)\
**Post date:** [July 14, 2025, 7:55am UTC](https://discuss.ai.google.dev/t/persistent-high-latency-with-gemini-2-5-pro/92047/5 "2025-07-14T07:55:53Z")

</div>

Hi @Krish_Varnakavi1,  
We are still encountering the same issue. Have you had a chance to investigate it?  
Thank you in advance

---

<div class="post-metadata">

**Author:** ![Bhavesh\_Jain](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/bhavesh_jain/32/32994_2.png) [@Bhavesh\_Jain](https://discuss.ai.google.dev/u/Bhavesh_Jain)\
**Post date:** [July 19, 2025, 5:41am UTC](https://discuss.ai.google.dev/t/persistent-high-latency-with-gemini-2-5-pro/92047/7 "2025-07-19T05:41:24Z")

</div>

Facing the same issue, for the request with 10k tokens, latency reaches 8-10 minutes, completely destroying the user experience on the app.

Also 429 errors randomly pop up even with 1RPM.

 ![Screenshot 2025-07-19 at 10.50.16 AM](https://d3qe71uytubmmx.cloudfront.net/original/3X/0/9/094f3f5240f950a51cd0d655736eddd78013287f.png)

---

<div class="post-metadata">

**Author:** ![FidFed](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/fidfed/32/29963_2.png) [@FidFed](https://discuss.ai.google.dev/u/FidFed)\
**Post date:** [July 26, 2025, 11:18pm UTC](https://discuss.ai.google.dev/t/persistent-high-latency-with-gemini-2-5-pro/92047/9 "2025-07-26T23:18:12Z")

</div>

I face the same issue, any news?