The implicit cache situation just got worst these 2 weeks on release of gemini 3.7 flash which works really nicely with my app except it now cost more than 2x as much because implicit caching is not working. I confirmed it is not an issue with my code because a swap to gpt model gets me >70% cache hit rate. with every turn and tool calls. With gemini 3.7 flash, this week, implicit cache didn’t trigger untill I have >12k input tokens! What’s worst is that it didn’t get triggered on every tool call! This got worst since I make this post showing how the threshold went up to ~10k and only cached the first ~8k in June-July 2026. How are you guys being affected by this issue?
Mathew
4
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Implicit Caching not Working on Gemini 2.5 Pro | 3 | 877 | June 16, 2025 | |
| Gemini 2.5 Flash implicit caching problem | 5 | 1111 | March 4, 2026 | |
| Gemini 2.5 Flash Lite: Implicit Caching Not Working Despite Meeting Documented Requirements | 1 | 675 | March 4, 2026 | |
| Have anyone checked out the implicit caching for gemini api, caches hits are inconsistent for me | 7 | 1176 | June 13, 2025 | |
| Flash implicit caching only works after 6k tokens vs the advertised 1k tokens | 1 | 347 | July 2, 2025 |