Begin constructing with Gemini 2.5 Flash

At this time we’re rolling out an early model of Gemini 2.5 Flash in preview by the Gemini API by way of Google AI Studio and Vertex AI. Constructing upon the favored basis of two.0 Flash, this new model delivers a significant improve in reasoning capabilities, whereas nonetheless prioritizing pace and value. Gemini 2.5 Flash is our first totally hybrid reasoning mannequin, giving builders the power to show considering on or off. The mannequin additionally permits builders to set considering budgets to seek out the precise tradeoff between high quality, price, and latency. Even with considering off, builders can preserve the quick speeds of two.0 Flash, and enhance efficiency.

Our Gemini 2.5 fashions are considering fashions, able to reasoning by their ideas earlier than responding. As a substitute of instantly producing an output, the mannequin can carry out a “considering” course of to raised perceive the immediate, break down advanced duties, and plan a response. On advanced duties that require a number of steps of reasoning (like fixing math issues or analyzing analysis questions), the considering course of permits the mannequin to reach at extra correct and complete solutions. In truth, Gemini 2.5 Flash performs strongly on Arduous Prompts in LMArena, second solely to 2.5 Professional.

Comparison table showing price and performance metrics for LLMs

2.5 Flash has comparable metrics to different main fashions for a fraction of the fee and measurement.

Our most cost-efficient considering mannequin

2.5 Flash continues to guide because the mannequin with the very best price-to-performance ratio.

Gemini 2.5 Flash price-to-performance comparison

Gemini 2.5 Flash provides one other mannequin to Google’s pareto frontier of price to high quality.*

Tremendous-grained controls to handle considering

We all know that totally different use circumstances have totally different tradeoffs in high quality, price, and latency. To offer builders flexibility, we’ve enabled setting a considering price range that provides fine-grained management over the utmost variety of tokens a mannequin can generate whereas considering. A better price range permits the mannequin to motive additional to enhance high quality. Importantly, although, the price range units a cap on how a lot 2.5 Flash can suppose, however the mannequin doesn’t use the complete price range if the immediate doesn’t require it.

Plot graphs show improvements in reasoning quality as thinking budget increases

Enhancements in reasoning high quality as considering price range will increase.

The mannequin is educated to know the way lengthy to suppose for a given immediate, and due to this fact routinely decides how a lot to suppose based mostly on the perceived job complexity.

If you wish to hold the bottom price and latency whereas nonetheless bettering efficiency over 2.0 Flash, set the considering price range to 0. You may also select to set a selected token price range for the considering part utilizing a parameter within the API or the slider in Google AI Studio and in Vertex AI. The price range can vary from 0 to 24576 tokens for two.5 Flash.

The next prompts show how a lot reasoning could also be used within the 2.5 Flash’s default mode.

Prompts requiring low reasoning:

Instance 1: “Thanks” in Spanish

Instance 2: What number of provinces does Canada have?

Prompts requiring medium reasoning:

Instance 1: You roll two cube. What’s the chance they add as much as 7?

Instance 2: My health club has pickup hours for basketball between 9-3pm on MWF and between 2-8pm on Tuesday and Saturday. If I work 9-6pm 5 days every week and wish to play 5 hours of basketball on weekdays, create a schedule for me to make all of it work.

Prompts requiring excessive reasoning:

Instance 1: A cantilever beam of size L=3m has an oblong cross-section (width b=0.1m, top h=0.2m) and is made from metal (E=200 GPa). It’s subjected to a uniformly distributed load w=5 kN/m alongside its total size and a degree load P=10 kN at its free finish. Calculate the utmost bending stress (σ_max).

Instance 2: Write a operate evaluate_cells(cells: Dict[str, str]) -> Dict[str, float] that computes the values of spreadsheet cells.

Every cell accommodates:

Or a formulation like "=A1 + B1 * 2" utilizing +, -, *,/ and different cells.

Necessities:

Resolve dependencies between cells.

Deal with operator priority (*/ earlier than +-).

Detect cycles and lift ValueError("Cycle detected at ").

No eval(). Use solely built-in libraries.

Begin constructing with Gemini 2.5 Flash right this moment

Gemini 2.5 Flash with considering capabilities is now out there in preview by way of the Gemini API in Google AI Studio and in Vertex AI, and in a devoted dropdown within the Gemini app. We encourage you to experiment with the thinking_budget parameter and discover how controllable reasoning can assist you remedy extra advanced issues.

from google import genai

consumer = genai.Consumer(api_key="GEMINI_API_KEY")

response = consumer.fashions.generate_content(
  mannequin="gemini-2.5-flash-preview-04-17",
  contents="You roll two cube. What’s the chance they add as much as 7?",
  config=genai.varieties.GenerateContentConfig(
    thinking_config=genai.varieties.ThinkingConfig(
      thinking_budget=1024
    )
  )
)

print(response.textual content)