Requesty
Sign in

identity

endpoint
Google LLC (Gemini API) logo

gemini-3.5-flashGoogle LLC (Gemini API)

in /1M$1.50input tokens
out /1M$9.00output tokens
context1.0M66K out
median ttft6.41smeasured
api
chat
hosting
Global
model lab
Google
weights
closed
added
May 2026
model id
google/gemini-3.5-flash

capabilities 6/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

2 providers serve gemini-3.5-flash. This page is one of them. Compare all endpoints

pricing

no markup
input
$1.50
output
$9.00
cache write
$1.58
cache read
$0.15

worked cost

Estimated cost for three request volumes
volumecost
100K in + 10K out$0.24
1M in + 100K out$2.40
10M in + 1M out$24.00

Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing

provider price, passed throughper 1M tokens

measured

through Sep 12
median ttft
6.41s
median tok/s
194.0
blended /1M
$1.33
cache hit
43.1%
answered
99.60%

Weekly aggregates from production traffic routed through Requesty to this endpoint. A metric with no qualifying sample is left out rather than filled in. Compare against the other providers

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
τ²-Bench95.6
GPQA Diamond92.1
Humanity's Last Exam41.3
Terminal-Bench Hard39.4
Intelligence Index33.6
5 evalsmean60.4

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-05-19.

policy

data terms
retention
none
trains on prompts
no
hosted in
Global

Terms are the provider's, not Requesty's: routing a request here puts it under them. Gemini API Terms

Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.

quickstart

openai compatible
google/gemini-3.5-flash

this id pins the google llc (gemini api) deployment, with no routing and no failover. the managed id on the canonical page routes across all 2 providers instead

main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="google/gemini-3.5-flash",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models

notes

reference

Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at sub-agent deployment, multi-step workflows, and long-horizon tasks at scale.

questions 6

How much does gemini-3.5-flash cost?
gemini-3.5-flash is priced at $1.50 per million input tokens and $9.00 per million output tokens when accessed via Requesty. Prompt caching is supported, which can cut effective input cost by up to 90% on repeated context. Requesty charges exactly what the upstream provider charges, we don't add markup.
What is the context window of gemini-3.5-flash?
gemini-3.5-flash has a context window of 1.0M tokens, with a maximum output of 66K tokens per response. That is roughly 1,398 words of input you can fit in a single prompt.
How does gemini-3.5-flash perform on benchmarks?
gemini-3.5-flash scores 95.6% on τ²-Bench, 92.1% on GPQA Diamond, 41.3% on Humanity's Last Exam. The benchmarks pane shows every published result, each normalised to 100.
What can gemini-3.5-flash do?
gemini-3.5-flash supports vision input, tool calling, extended reasoning, prompt caching, web search, structured outputs (JSON schema). You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use gemini-3.5-flash with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "google/gemini-3.5-flash". The quickstart pane shows Python, JavaScript and cURL snippets.
Can I run gemini-3.5-flash through Requesty?
Yes. gemini-3.5-flash runs through Requesty's OpenAI-compatible API, served from Google LLC (Gemini API). You do not host the model yourself: point base_url at Requesty, set the model to "google/gemini-3.5-flash", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.

more from google llc (gemini api) 8

Other Google LLC (Gemini API) endpoints
endpointctxin /M
gemini-3.6-flash:flex1.0M$0.38
gemini-3.6-flash1.0M$1.50
gemini-3.5-flash-lite1.0M$0.30
gemini-3.5-flash-lite:flex1.0M$0.15
gemini-3.1-flash-image131K$0.50
gemini-3-pro-image1.0M$2.00
gemini-3.5-flash:flex1.0M$0.75
gemini-3.1-flash-lite:flex1.0M$0.13

call gemini-3.5-flash through one endpoint

One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology

gemini-3.5-flashgoogle llc (gemini api)in $1.50 /1Mout $9.00 /1Mctx 1.0Mttft 6.41shosted Global2 providers serve this model