What's new in Gemini 3.7 Flash

Latest model Other models

Gemini 3.7 Flash (gemini-3.7-flash) is generally available (GA) and ready for production use. It is our most intelligent workhorse model yet for coding and agents.

This guide explains what's new in Gemini 3.7 Flash, API changes, code examples, and migration guidance.

New model

Gemini 3.7 Flash supports a 1M token context window, 64k max output tokens, tunable thinking levels (low, medium, high), and the same suite of built-in tools as 3.6 Flash.

For complete specs, see the Gemini 3.7 Flash model page. For detailed pricing, see the pricing page.

Quickstart

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.7-flash",
    input="Write a responsive navigation component in React with smooth animations and dark mode toggle."
)

print(interaction.output_text)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
  model: "gemini-3.7-flash",
  input: "Write a responsive navigation component in React with smooth animations and dark mode toggle.",
});

console.log(interaction.output_text);

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();
CreateModelInteraction req = CreateModelInteraction.builder()
    .model(Model.of("gemini-3.7-flash"))
    .input(InteractionsInput.of("Write a responsive navigation component in React with smooth animations and dark mode toggle."))
    .build();
Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "model": "gemini-3.7-flash",
    "input": "Write a responsive navigation component in React with smooth animations and dark mode toggle."
  }'

What's new in Gemini 3.7 Flash

• Coding and agentic tasks: Significantly higher quality on real-world software engineering and agentic benchmarks, improving issue resolution and reducing failed agent loops.
• Web development and stronger design parity: Generates higher-fidelity desktop and web application code directly from design mocks, with strong gains in design adherence and in auditing existing codebases against mocks to verify 1:1 design parity.
• Promotional pricing: Gemini 3.7 Flash will be available at an introductory price of $0.75/1M input tokens and $3.75/1M output tokens. We're also applying this new rate to 3.6 Flash. Introductory pricing expires on December 31, 2026; after, $1.50/1M input tokens and $7.50/1M output tokens will apply.

Choosing the right model

Reference the following table to review recommended migration targets for your workloads. To upgrade from Gemini 3.5 Flash, Gemini 3 Flash (Preview), or Gemini 3.1 Pro, ensure you remove deprecated sampling parameters (temperature, top_p, top_k) and prefilled model turns. Gemini 3.6 Flash already no longer supported these parameters.

Understanding reasoning levels

Gemini 3.7 Flash gives developers flexible control over latency and intelligence by adjusting the model's thinking level:

• Low thinking effort: Reduces time-to-answer for latency-critical tasks like incident response pipelines, real-time chat, writing drafts, and fast data analysis.
• Medium (default): Best quality for most tasks. Recommended for complex code and agentic use cases, with higher first-pass accuracy.
• High thinking effort: Maximizes the model's ability to think and use tools. Best for complex reasoning, hard math, and difficult coding and agent tasks. Allows extended thoughts and function calls, with higher token consumption and cost.

To configure thinking levels in Gemini 3.7 Flash:

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.7-flash",
    input="Analyze this payment processing pipeline for race conditions during retry attempts and rewrite the transaction locks safely.",
    generation_config={
        "thinking_level": "medium"  # Balanced reasoning effort for complex tasks
    }
)

print(interaction.output_text)

For multi-language code examples (JavaScript, Java, Go, REST) and in-depth reasoning concepts, see Understanding reasoning levels in Gemini 3.8 Flash.

Antigravity agent support

Gemini 3.7 Flash introduced support for powering the Antigravity agent in Gemini Managed Agents and the Google Antigravity SDK.

For current code samples and the latest default agent configuration, see the Antigravity agent guide and the Gemini 3.8 Flash guide.

Migration checklist

  `/gemini-api-dev migrate my app to Gemini 3.7 Flash`

Migrate to gemini-3.7-flash

• Update Model ID: Change your target model string to gemini-3.7-flash.
• Configure thinking level: Replace thinking_budget with the string enum thinking_level, and set it to "low", "medium" (default), or "high" as needed for your workload.
• Apply Gemini 3 API parameter changes: Remove deprecated sampling parameters (temperature, top_p, top_k), candidate_count (unsupported in Gemini 3 and later), and prefilled model turns. See Gemini 3.6 API changes and parameter updates.
• Baseline Gemini 3.x requirements: For function calling strict response matching, SDK updates, and thought signature preservation, see the Gemini 3.5 Migration Checklist.

Pricing

For complete pricing details and introductory rates, see the pricing page.

Next steps

• Review API specs on the Models Overview.
• Explore multi-agent orchestration in the Interactions API Guide.
• Test and refine prompts in Google AI Studio.