---
id: provider-cache-hit-rate/2026-06
series: provider-cache-hit-rate
title: Prompt cache hit rate by provider, June 2026
period: 2026-06
period_start: 2026-06-01
period_end: 2026-06-30
updated: 2026-11-11
license: CC BY 4.0
canonical: https://www.requesty.ai/data/provider-cache-hit-rate/2026-06
latest: https://www.requesty.ai/data/provider-cache-hit-rate
---

# Prompt cache hit rate by provider, June 2026

> DeepSeek served 85.5% of input tokens from cache in June 2026, the highest among major providers. The median major provider served 55.2%.

Question: What share of input tokens do LLM providers serve from prompt cache?

## Key findings

1. DeepSeek leads at 85.5%; Novita is lowest at 23.1%.
2. 3 of 12 major providers served at least 80% of input tokens from cache.
3. DeepInfra moved the most since May 2026: cache hit rate went from 12.6% to 38.3% (+25.7 pp).

## Data

| Provider | Cache hit rate | Traffic share | Organizations (band) |
| --- | --- | --- | --- |
| DeepSeek | 85.50% | 8.00% | 100-499 |
| Anthropic | 84.89% | 24.40% | 500+ |
| Fireworks | 84.70% | 0.73% | 100-499 |
| Vertex (Claude) | 73.03% | 2.83% | 100-499 |
| Bedrock | 67.71% | 3.82% | 500+ |
| Azure | 64.97% | 5.39% | 100-499 |
| OpenAI | 45.46% | 30.70% | 500+ |
| DeepInfra | 38.33% | 1.73% | 100-499 |
| xAI | 36.92% | 1.09% | 100-499 |
| Mistral | 32.36% | 0.86% | 100-499 |
| Vertex (Gemini) | 26.66% | 17.84% | 500+ |
| Novita | 23.05% | 0.96% | 100-499 |

## Method

- Cache hit rate is cached input tokens divided by input tokens, the same definition /rankings uses.
- Providers that report no cached tokens are left out of the chart. Only providers with at least 0.5% of published traffic are shown.
- A row is published only when it has at least 20 requests, at least 5 distinct organizations, and no single organization above 80% of its traffic. These are the same floors /rankings uses. Rows below the floors are withheld, not estimated.
- Only shares, rates, medians and organization bands are published. Absolute request, token and spend totals stay private.

## Caveats

- Hit rate depends on workload. Long agent sessions with a stable prefix cache far better than one-off requests.
- Providers report cached tokens differently. Some only count explicit cache reads.

## Cite as

Requesty (2026). Prompt cache hit rate by provider, June 2026. Requesty Data. https://www.requesty.ai/data/provider-cache-hit-rate/2026-06

```bibtex
@misc{requesty_provider_cache_hit_rate_2026_06,
  author       = {{Requesty}},
  title        = {Prompt cache hit rate by provider, June 2026},
  year         = {2026},
  howpublished = {\url{https://www.requesty.ai/data/provider-cache-hit-rate/2026-06}},
  note         = {Requesty Data}
}
```

Source: Requesty production gateway. License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/).
Downloads: [JSON](https://www.requesty.ai/data/provider-cache-hit-rate/2026-06/data.json) · [CSV](https://www.requesty.ai/data/provider-cache-hit-rate/2026-06/data.csv) · [Markdown](https://www.requesty.ai/data/provider-cache-hit-rate/2026-06/data.md)