Google · implicit caching
Gemini 3.5 Flash
Cheap, fast multimodal model with implicit caching and a very large window - a strong default for document-heavy RAG.
Specifications
At a glance.
| Provider | |
| Family | gemini-3.5 |
| Released | 2026-05 |
| License | Proprietary |
| Context window | 1M tokens |
| Max output | 66K tokens |
| Modalities | text, image, video, audio, pdf |
| Tool calling | Yes |
| Reasoning mode | Yes |
| Caching | implicit |
| Batch discount | 50% off |
Measured by Zumik
What reuse looks like here.
What you actually pay once caching works.
At a typical 55% prefix reuse, a million input tokens on Gemini 3.5 Flash effectively costs $0.76 instead of $1.50 - blending to roughly $2.82 with a 25% output share. Background work drops a further 50% on the batch tier.
Estimate it for your workloadRoutes through these aliases:
Call it
Same OpenAI client, this model.
from openai import OpenAI
client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")
r = client.responses.create(
model="gemini-3-5-flash", # or an alias like auto.cheapest
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseSimilar models
Other options for these workloads.
Frequently asked
Gemini 3.5 Flash, answered.
How much does Gemini 3.5 Flash cost?
Gemini 3.5 Flash is $1.50 per million input tokens and $9.00 per million output tokens through Zumik. Cache reads are $0.15 per million, a 90% discount on input.
What is Gemini 3.5 Flash's context window?
Gemini 3.5 Flash supports a 1M-token context window with up to 66K output tokens.
Does Gemini 3.5 Flash support prompt caching?
Yes. Google Gemini uses Implicit context caching caching. In the Zumik corpus, Gemini 3.5 Flash shows a median cache capture of 85% on agent workloads.
Which Zumik aliases route to Gemini 3.5 Flash?
Gemini 3.5 Flash is a candidate for the auto.cheapest, vision.balanced, auto.fast aliases, selected when it wins under current routing policy.
Run Gemini 3.5 Flash with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.