---
id: latency-yoy-october-2026
slug: provider-latency-yoy-october-2026
title: "p50 latency year over year: October 2025 to October 2026"
topic: latency
period: Oct 2025 to Oct 2026
updated: 2026-11-11
license: CC BY 4.0
canonical: https://www.requesty.ai/data/provider-latency-yoy-october-2026
---

# p50 latency year over year: October 2025 to October 2026

> Did AI providers get faster over the past year? Comparing October 2025 with October 2026, Nebius median latency fell 90%, from 2.8s to 288ms. OpenAI rose from 556ms to 2.3s as its traffic shifted to larger reasoning models.

*Topic: Latency and performance. Period: Oct 2025 to Oct 2026. Last updated 2026-11-11.*

## Why it matters

Year over year latency changes mix two effects: provider infrastructure and the models customers run. A rise usually means heavier models, not a slower provider.

## Questions this answers

- Have LLM providers gotten faster in the last year?
- Which provider improved latency the most?
- Why did some providers get slower?

## Key findings

1. Nebius: 2.8s to 288ms (-90%).
2. Vertex (Gemini): 2.8s to 816ms (-71%).
3. Vertex (Claude): 6.3s to 2.9s (-54%).
4. Anthropic: 4.2s to 4.0s (-5%).
5. Bedrock: 3.9s to 4.3s (+10%).
6. xAI: 4.2s to 5.0s (+19%).
7. OpenAI: 556ms to 2.3s (+306%).

## Data

| Provider | Oct 2025 p50 (milliseconds) | Oct 2026 p50 (milliseconds) | YoY delta (percent) |
| --- | --- | --- | --- |
| Nebius | 2.77 s | 288 ms | -89.61% |
| Vertex (Gemini) | 2.77 s | 816 ms | -70.56% |
| Vertex (Claude) | 6.28 s | 2.87 s | -54.35% |
| Anthropic | 4.21 s | 4.02 s | -4.68% |
| Bedrock | 3.94 s | 4.32 s | 9.86% |
| xAI | 4.19 s | 4.97 s | 18.53% |
| OpenAI | 556 ms | 2.25 s | 305.81% |

## Caveats

- Providers with at least 50k requests in both months.
- The model mix on each provider changed between the two months.

## Cite as

**APA.** Requesty (2026). p50 latency year over year: October 2025 to October 2026. Requesty Data. https://www.requesty.ai/data/provider-latency-yoy-october-2026

```bibtex
@misc{requesty_provider_latency_yoy_october_2026,
  author       = {{Requesty}},
  title        = {p50 latency year over year: October 2025 to October 2026},
  year         = {2026},
  howpublished = {\url{https://www.requesty.ai/data/provider-latency-yoy-october-2026}},
  note         = {Requesty Data}
}
```

---

Downloads: [JSON](https://www.requesty.ai/data/provider-latency-yoy-october-2026/data.json) · [CSV](https://www.requesty.ai/data/provider-latency-yoy-october-2026/data.csv) · [Markdown](https://www.requesty.ai/data/provider-latency-yoy-october-2026/data.md)