Gemini 3.5 Flash

Cheap, fast multimodal model with implicit caching and a very large window - a strong default for document-heavy RAG.

$1.50
Input / 1M tokens
$9.00
Output / 1M tokens
$0.15
Cache read · −90%
1M
Context window

At a glance.

ProviderGoogle
Familygemini-3.5
Released2026-05
LicenseProprietary
Context window1M tokens
Max output66K tokens
Modalitiestext, image, video, audio, pdf
Tool callingYes
Reasoning modeYes
Cachingimplicit
Batch discount50% off

What reuse looks like here.

Gemini 3.5 Flash · agent trafficper request
Total input100%
Candidate reuse62%
Realized reuse50%
Capture rate81%
150ms
Warm TTFT · −61% vs cold
220
Output tokens / sec
Reuse economics

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 workload
Best for
multimodalhigh-volumelow-latency

Routes through these aliases:

Same OpenAI client, this model.

python
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 reuse

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 81% 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.