Zumik
Sign inSign up

Google · implicit caching

Gemini Flash-Lite Latest

Gemini Flash-Lite Latest on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.

Call it through ZumikAbout Google Gemini
$0.10
Input / 1M tokens
$0.40
Output / 1M tokens
$0.03
Cache read · −75%
1M
Context window

Specifications

At a glance.

ProviderGoogle
Familygemini
Released2025-09
LicenseProprietary
Context window1M tokens
Max output66K tokens
Modalitiestext, image, audio, video, pdf
Tool callingYes
Reasoning modeYes
Cachingimplicit
Batch discount50% off

Measured by Zumik

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for Gemini Flash-Lite Latest are live, but it is outside the flagship set Zumik benchmarks in depth, so measured reuse, capture, and warm TTFT are not shown yet. Run a workload estimate or route it by id to start collecting traces.

Reuse economics

What you actually pay once caching works.

At a typical 55% prefix reuse, a million input tokens on Gemini Flash-Lite Latest effectively costs $0.06 instead of $0.10 - blending to roughly $0.14 with a 25% output share. Background work drops a further 50% on the batch tier.

Estimate it for your workload
Best for
textimageaudiovideopdf

Route it directly by id, or let an alias pick it when it wins under policy.

Call it

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-flash-lite-latest",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

Frequently asked

Gemini Flash-Lite Latest, answered.

How much does Gemini Flash-Lite Latest cost?

Gemini Flash-Lite Latest is $0.10 per million input tokens and $0.40 per million output tokens through Zumik. Cache reads are $0.03 per million, a 75% discount on input.

What is Gemini Flash-Lite Latest's context window?

Gemini Flash-Lite Latest supports a 1M-token context window with up to 66K output tokens.

Does Gemini Flash-Lite Latest support prompt caching?

Yes. Google Gemini uses Implicit context caching caching. In the Zumik corpus, Gemini Flash-Lite Latest shows a median cache capture of 80% on agent workloads.

Run Gemini Flash-Lite Latest with reuse measured.

Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.

Migration quickstartBack to catalog