Gemini 2.5 Flash-Lite pricing, context window and limits
Gemini 2.5 Flash-Lite costs $0.1 per million input tokens and $0.4 per million output tokens at Google Vertex AI list price. It accepts up to 1,048,576 tokens of context and returns up to 65,536 tokens.
- Model id
vertex/gemini-2.5-flash-lite - Snapshot
What does Gemini 2.5 Flash-Lite cost?
| Input | $0.1 |
|---|---|
| Output | $0.4 |
| Cached input (read) | $0.01 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Gemini 2.5 Flash-Lite read and write?
| Context window | 1,048,576 |
|---|---|
| Max output | 65,536 |
What can Gemini 2.5 Flash-Lite do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text, image, audio, video, pdf |
| Output | text |
What does a request to Gemini 2.5 Flash-Lite cost?
| A typical request: 1,000 tokens in, 500 out | $0.0003 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0014 |
| 1,000 typical requests | $0.3 |
| 1 million tokens in and 1 million out | $0.5 |
Input read from the provider's prompt cache costs $0.01 per million tokens instead of $0.1, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.00021 instead of $0.0003.
Among 12 Google Vertex AI models with a published price, Gemini 2.5 Flash-Lite is the cheapest by input price. Its context window is the largest of 12. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Gemini 2.5 Flash-Lite through DVARA?
Configure the vertex-ai provider in the DVARA LLM Gateway and send the model id vertex/gemini-2.5-flash-lite. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Google Vertex AI models are there?
- Gemini 2.5 Flash$0.3 in · $2.5 out · 1.05M context
- Gemini 2.5 Pro$1.25 in · $10 out · 1.05M context
- Gemini 3.1 Flash Lite$0.25 in · $1.5 out · 1.05M context
- Gemini 3.1 Pro Preview$2 in · $12 out · 1.05M context
- Gemini 3.5 Flash$1.5 in · $9 out · 1.05M context
- Gemini 3.5 Flash Lite$0.3 in · $2.5 out · 1.05M context
- Gemini 3.6 Flash$0.75 in · $3.75 out · 1.05M context
- Gemini 3.7 Flash$0.75 in · $3.75 out · 1.05M context
- Gemini 3.8 Flash$0.75 in · $3.75 out · 1.05M context
- Gemini 4 Argon$2 in · $10 out · 1.05M context
- Gemini Embedding 001$0.15 in · $0 out · 2K context
Which models from other providers are similar to Gemini 2.5 Flash-Lite?
These are the closest in context window and input price, one per provider.
- Gemini 2.5 Flash-LiteGoogle Gemini · $0.1 in · $0.4 out · 1.05M context
- GPT-4.1 nanoOpenAI · $0.1 in · $0.4 out · 1.05M context
- GPT-6 Luna (Global)Amazon Bedrock · $0.1 in · $0.5 out · 1.05M context
- Claude Haiku 5.5Anthropic · $0.1 in · $0.5 out · 1M context
- Qwen3.8 Omni FlashAlibaba Qwen · $0.113 in · $0.382 out · 1M context