Gemini 2.5 Flash is Google’s high-performance workhorse model, designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in thinking, and a max tokens for reasoning parameter lets you tune its performance.
A range is the low and high price across our routes: you pay the price of the route that answers, and the cheapest goes first. Struck through is the developer's official price.
$0.075–$0.15
official price $0.30 official
$0.0075–$0.015
official price $0.03 official
$0.625–$1.25
official price $2.50 official
How fast the model answers over every route we serve it from: throughput is tokens written per second, time to first token is how soon the answer starts, end-to-end latency is the whole request.
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
Gemini 2.5 Flash is Google’s high-performance workhorse model, designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in thinking, and a max tokens for reasoning parameter lets you tune its performance.
On NagaAI, Gemini 2.5 Flash costs from $0.075 per 1M input tokens and from $0.625 per 1M output tokens. You pay only for what you use, with no subscription.
Gemini 2.5 Flash reads up to 1.0M tokens in one request, counting the prompt and the answer together.
Yes. Gemini 2.5 Flash can call your functions as tools and can answer in a JSON schema you give it.
It takes text, images, files and audio as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.