gemini-2.5-flash-lite
Google's smallest and most cost effective model, built for at scale usage.
👁Vision🧠Reasoning🔧Tool calling⚡Caching
Specifications
Context window1.0M tokens
Max output66K tokens
API typechat
AddedMay 20, 2025
Model IDvertex/gemini-2.5-flash-lite@europe-west4
Data retentionNo
Used for trainingNo
Provider location🇺🇸 US / 🇪🇺 EU
Privacy policyVertex AI Data Governance →
Benchmarks
Benchmarks haven't been published yet for this exact variant.
Some variants (region-specific deployments, highspeed tiers) share benchmarks with their base model — check the base model page or the Google LLC (Vertex AI) models overview.
Pricing
Input / 1M
$0.10
Output / 1M
$0.40
Cache write / 1M
$0.18
Cache read / 1M
$0.01
Estimated cost
100K input + 10K output$0.0140
1M input + 100K output$0.14
10M input + 1M output$1.40
Requesty charges exactly what the upstream provider charges — no markup, no per-request fees. Prompt caching and smart routing can reduce effective cost by 30-80%.
Quickstart
Drop-in compatible with the OpenAI SDK. Change the base URL, swap in your Requesty API key, and set the model to vertex/gemini-2.5-flash-lite@europe-west4.
123456789101112131415from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1", ) response = client.chat.completions.create( model="vertex/gemini-2.5-flash-lite@europe-west4", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ], ) print(response.choices[0].message.content)
Other Google LLC (Vertex AI) models
Frequently asked questions
How much does gemini-2.5-flash-lite cost?
gemini-2.5-flash-lite is priced at $0.10 per million input tokens and $0.40 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-2.5-flash-lite?
gemini-2.5-flash-lite has a context window of 1.0M tokens, with a maximum output of 66K tokens per response. That's roughly 1,398 words of input you can fit in a single prompt.
What can gemini-2.5-flash-lite do?
gemini-2.5-flash-lite supports vision input, tool calling, extended reasoning, prompt caching. You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use gemini-2.5-flash-lite 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 "vertex/gemini-2.5-flash-lite@europe-west4". The Quickstart above shows Python, JavaScript and cURL snippets.
What region is this deployment?
This variant of gemini-2.5-flash-lite is deployed in europe-west4. Region-specific endpoints matter for data residency, latency to your users, and compliance requirements (GDPR, HIPAA). Other regions for the same model may be listed on the Google LLC (Vertex AI) provider page.
Access gemini-2.5-flash-lite through Requesty
One API key, 400+ models, OpenAI-compatible. No markup on provider prices, automatic failover, and smart caching built-in.