Google · implicit caching
Gemini Flash Latest
Gemini Flash Latest on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
Specifications
At a glance.
| Provider | |
| Family | gemini |
| Released | 2025-09 |
| License | Proprietary |
| Context window | 1M tokens |
| Max output | 66K tokens |
| Modalities | text, image, audio, video, pdf |
| Tool calling | Yes |
| Reasoning mode | Yes |
| Caching | implicit |
| Batch discount | 50% off |
Measured by Zumik
What reuse looks like here.
Pricing, context, and capabilities for Gemini Flash 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.
What you actually pay once caching works.
At a typical 55% prefix reuse, a million input tokens on Gemini Flash Latest effectively costs $0.18 instead of $0.30 - blending to roughly $0.76 with a 25% output share. Background work drops a further 50% on the batch tier.
Estimate it for your workloadRoute it directly by id, or let an alias pick it when it wins under policy.
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-flash-latest",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Gemini Flash Latest, answered.
How much does Gemini Flash Latest cost?
Gemini Flash Latest is $0.30 per million input tokens and $2.50 per million output tokens through Zumik. Cache reads are $0.07 per million, a 75% discount on input.
What is Gemini Flash Latest's context window?
Gemini Flash Latest supports a 1M-token context window with up to 66K output tokens.
Does Gemini Flash Latest support prompt caching?
Yes. Google Gemini uses Implicit context caching caching. In the Zumik corpus, Gemini Flash Latest shows a median cache capture of 83% on agent workloads.
Run Gemini Flash Latest with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.