Unlock exclusive introductory pricing for the newly launched Gemini 3.5 Flash.
G

Gemini 3.6 Flash

Wejล›cie:$1.2/M
Wyjล›cie:$6/M
Wydano:Jul 21, 2026

Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at code generation, agentic execution, and spatial reasoning. This model is particularly effective for rapid agentic loops involving complex coding cycles and iterations.

Nowy
Uลผycie komercyjne

Playground dla Gemini 3.6 Flash

Poznaj Playground Gemini 3.6 Flash โ€” interaktywne ล›rodowisko do testowania modeli i uruchamiania zapytaล„ w czasie rzeczywistym. Wyprรณbuj prompty, dostosuj parametry i iteruj natychmiast, aby przyspieszyฤ‡ rozwรณj i zweryfikowaฤ‡ przypadki uลผycia.

Technical Specifications of Gemini 3.6 Flash

ItemGemini 3.6 Flash
ProviderGoogle DeepMind
Model IDgemini-3.6-flash
Model familyGemini 3.x
AvailabilityGeneral Availability (GA)
Input typesText, Image, Video, Audio, PDF
Output typesText
Context window1,048,576 tokens
Maximum output65,536 tokens
ThinkingSupported (medium / high)
Function callingYes
Code executionYes
File SearchYes
URL ContextYes
Search GroundingYes
Computer UsePreview
Structured OutputYes
CachingSupported

Source: Google Gemini API documentation.

What is Gemini 3.6 Flash?

Gemini 3.6 Flash is Google's newest production-ready Flash model, designed to deliver frontier-level intelligence while maintaining the low latency and cost efficiency that the Flash series is known for. It is optimized for coding, multimodal understanding, reasoning, and agentic workflows.

Compared with Gemini 3.5 Flash, the model improves code generation quality, reasoning accuracy, tool usage, and token efficiency while supporting a massive 1 million-token context window. Google positions it as the default workhorse model for developers building AI agents and complex automation systems.

Main Features of Gemini 3.6 Flash

  • Supports 1M-token long-context processing.
  • Native multimodal inputs including text, images, video, audio, and PDF documents.
  • Strong improvements in code generation and software engineering tasks.
  • Built-in support for Function Calling, File Search, URL Context, Search Grounding, and Computer Use.
  • More token-efficient than Gemini 3.5 Flash, reducing inference cost while maintaining higher quality.
  • Designed for multi-step AI agents and autonomous workflows.

Benchmark Performance

Google reports that Gemini 3.6 Flash delivers stronger coding, reasoning, and multimodal performance than Gemini 3.5 Flash while using significantly fewer output tokens. The company highlights improved performance on internal coding and agentic benchmarks and states the model can reduce output token usage by up to 65% on certain software engineering evaluations such as DeepSWE, lowering overall inference costs. Google has not published comprehensive public benchmark tables (e.g., MMLU, GPQA, SWE-bench Verified) for this release.

Gemini 3.6 Flash

Gemini 3.6 Flash vs Gemini 3.5 Flash vs Gemini 3.1 Pro

AspectGemini 3.6 FlashGemini 3.5 FlashGemini 3.1 Pro
ReleaseJuly 21, 2026 (GA)Earlier 2026~Feb 2026 (Preview)
PositioningEfficient workhorse for agents, coding, multimodalPrevious agentic Flash modelAdvanced Pro-tier reasoning
Pricing (per 1M tokens)Input: $1.50Output: $7.50Input: $1.50Output: $9.00Higher (e.g., ~$2 input / $12 output)
Token Efficiency17% fewer output tokens vs 3.5 Flash; fewer steps/tool callsBaselineLess efficient in agentic workflows
SpeedHigh (Flash family)HighSlower than Flash models
Context Window1M tokens1M tokensLikely similar
StrengthsCoding, knowledge work, multimodal (charts/documents), computer use, agentic efficiencyGood agentic/coding balanceDeeper reasoning on complex problems

Quick Summary

  • 3.6 Flash โ†’ Best overall choice for most users right now: faster, cheaper per task, more efficient than 3.5 Flash, and outperforms 3.1 Pro on many practical/agentic benchmarks.
  • 3.5 Flash โ†’ Solid predecessor; still capable but being superseded by 3.6 Flash (higher output token cost, less efficient).
  • 3.1 Pro โ†’ Stronger in some deep reasoning scenarios but slower, more expensive, and generally lags the newer Flash models in speed, efficiency, and many real-world/agentic tasks.

Limitations

  • Image generation is not supported directly.
  • Audio generation is unavailable.
  • Computer Use remains in Preview.
  • Some legacy generation parameters (temperature, top_p, top_k) have been removed from the new API interface.
  • Best performance is achieved through the latest Gemini Interactions API.

How to Access Gemini 3.6 Flash API

Step 1: Get API Access

Log in to cometAPI. If you are not our user yet, please register first. Sign into yourย CometAPI console. Get the access credential API key of the interface. Click โ€œAdd Tokenโ€ at the API token in the personal center, get the token key: sk-xxxxx and submit.

cometapi-key

Step 2: Send Requests to Gemini 3.6 Flash API

Select the โ€œ gemini-3.6-flash" "gemini-3.6-flash-thinkingโ€ endpoint to send the API request and set the request body. The request method and request body are obtained from our website API doc. Our website also provides Apifox test for your convenience. Replace <YOUR_API_KEY> with your actual CometAPI key from your account. base url isย Gemini Generating Content

Insert your question or request into the content fieldโ€”this is what the model will respond to . Process the API response to get the generated answer.

Step 3: Process Responses

The API returns structured candidate responses including generated text, citations, safety metadata, and optional tool outputs.

FAQ

Cennik dla Gemini 3.6 Flash

Poznaj konkurencyjne ceny dla Gemini 3.6 Flash, zaprojektowane tak, aby pasowaล‚y do rรณลผnych budลผetรณw i potrzeb uลผytkowania. Nasze elastyczne plany zapewniajฤ…, ลผe pล‚acisz tylko za to, czego uลผywasz, co uล‚atwia skalowanie w miarฤ™ wzrostu Twoich wymagaล„. Odkryj, jak Gemini 3.6 Flash moลผe ulepszyฤ‡ Twoje projekty przy jednoczesnym utrzymaniu kosztรณw na rozsฤ…dnym poziomie.

ModelComet Price (USD / M Tokens)Official Price (USD / M Tokens)Discount
gemini-3.6-flash
Wejล›cie:$1.2/M
Wyjล›cie:$6/M
Wejล›cie:$1.5/M
Wyjล›cie:$7.5/M
-20%

Przykล‚adowy kod i API dla Gemini 3.6 Flash

Uzyskaj dostฤ™p do kompleksowego przykล‚adowego kodu i zasobรณw API dla Gemini 3.6 Flash, aby usprawniฤ‡ proces integracji. Nasza szczegรณล‚owa dokumentacja zapewnia wskazรณwki krok po kroku, pomagajฤ…c wykorzystaฤ‡ peล‚ny potencjaล‚ Gemini 3.6 Flash w Twoich projektach.

#!/bin/bash

curl "https://api.cometapi.com/v1beta/models/gemini-3.6-flash:generateContent" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Write a three.js script that renders an interactive 3D robot."
          }
        ]
      }
    ],
    "generationConfig": {
      "maxOutputTokens": 8192
    }
  }'

cURL Code Example

#!/bin/bash

curl "https://api.cometapi.com/v1beta/models/gemini-3.6-flash:generateContent" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Write a three.js script that renders an interactive 3D robot."
          }
        ]
      }
    ],
    "generationConfig": {
      "maxOutputTokens": 8192
    }
  }'

Python Code Example

import os

from google import genai
from google.genai import types


client = genai.Client(
    api_key=os.environ["COMETAPI_KEY"],
    http_options={
        "api_version": "v1beta",
        "base_url": "https://api.cometapi.com",
        "retry_options": {"attempts": 1},
    },
)

response = client.models.generate_content(
    model="gemini-3.6-flash",
    contents="Write a three.js script that renders an interactive 3D robot.",
    config=types.GenerateContentConfig(max_output_tokens=8192),
)

print(f"Response ID: {response.response_id}")
print(f"Model Version: {response.model_version}")
print(f"Finish Reason: {response.candidates[0].finish_reason}")
print(response.text)

JavaScript Code Example

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


const ai = new GoogleGenAI({
  apiKey: process.env.COMETAPI_KEY,
  httpOptions: {
    apiVersion: "v1beta",
    baseUrl: "https://api.cometapi.com",
    retryOptions: { attempts: 1 },
  },
});

const response = await ai.models.generateContent({
  model: "gemini-3.6-flash",
  contents: "Write a three.js script that renders an interactive 3D robot.",
  config: {
    maxOutputTokens: 8192,
  },
});

console.log(`Response ID: ${response.responseId}`);
console.log(`Model Version: ${response.modelVersion}`);
console.log(`Finish Reason: ${response.candidates[0].finishReason}`);
console.log(response.text);

Uptime

Wskaลบnik sukcesu ลผฤ…daล„ z ostatnich 30 dni, odzwierciedlajฤ…cy niezawodnoล›ฤ‡ kaลผdego dostawcy modelu. CometAPI monitoruje wszystkich podล‚ฤ…czonych dostawcรณw w czasie rzeczywistym przez caล‚ฤ… dobฤ™.

RespondLIVE
3408msAvg. Response
UptimeLIVE
100.0%Avg. Uptime

Wersje modelu Gemini 3.6 Flash

Powody, dla ktรณrych Gemini 3.6 Flash posiada wiele migawek, mogฤ… obejmowaฤ‡ takie czynniki jak: rรณลผnice w wynikach po aktualizacjach wymagajฤ…ce starszych migawek dla zachowania spรณjnoล›ci, zapewnienie programistom okresu przejล›ciowego na adaptacjฤ™ i migracjฤ™, oraz rรณลผne migawki odpowiadajฤ…ce globalnym lub regionalnym punktom koล„cowym w celu optymalizacji doล›wiadczenia uลผytkownika. Aby poznaฤ‡ szczegรณล‚owe rรณลผnice miฤ™dzy wersjami, zapoznaj siฤ™ z oficjalnฤ… dokumentacjฤ….

Version
gemini-3.6-flash