Gemini 3 Flash API

Try this model

Gemini 3 Flash Preview is a fast, efficient variant of Gemini 3 designed for low-latency multimodal applications.

Modalities: Text, Image, Audio, VideoText
In / Out price: $0.5/$3per 1M
Context window: 1M tokens
Released: Dec 17, 2025

Gemini 3 Flash overview

Gemini 3 Flash by Google

Gemini 3 Flash Preview is Google’s fast multimodal LLM API for agents, coding, and docs with pro-level control.

Gemini 3 Flash specs

Model ID: google/gemini-3-flash-preview
Developer: Google
Context window: 1,000,000 tokens
Max output: 65,536 tokens
Input: Text, Image, Audio, Video
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Gemini 3 Flash API Overview

Gemini 3 Flash (Preview) is built to deliver frontier-ish capability at Flash speed, great for agentic workflows, coding helpers, document intelligence, and high-volume production apps where latency and cost matter as much as quality. It’s rolling out across Gemini API (AI Studio), Vertex AI, and other Google dev surfaces, and it’s also becoming the default in parts of the consumer Gemini experience.

Technical Specifications

Architecture: Transformer-based generative multimodal LLM
Context Length: Up to 1M tokens input / 64K tokens output
Capabilities: Text + multimodal understanding (images, audio, video, PDFs), structured outputs, tool/function calling, agent-friendly behaviors.
Knowledge cutoff: Jan 2025
Inference features: Reasoning (“thinking”) is supported, and output pricing explicitly includes thinking tokens in Gemini API pricing.

Performance Benchmarks

Speed / throughput: Independent pre-release testing reported ~218 output tokens/sec for Gemini 3 Flash Preview (fast enough for real-time-ish agent loops and high-QPS backends).
Quality vs prior Flash: Google/DeepMind positions Flash as meaningfully stronger than previous Flash generations for difficult extraction and doc tasks.

Quality Improvements

More nuanced answers at lower latency than the prior default Flash in Gemini (per Google’s positioning and reporting around the rollout).
Stronger document/extraction performance: DeepMind highlights a relative improvement (~15%) in overall accuracy vs Gemini 2.5 Flash for hard extraction scenarios (e.g., handwriting, long contracts, financial docs).
Agent readiness: Designed to keep “Pro-grade” reasoning foundations while staying Flash-fast for multi-step tool use and workflows.

New Features & Technical Upgrades

1M-token long context (with 64K output) for long docs, multi-file projects, and persistent agent state.
Multimodal tool/function calling (including support for multimodal content in certain function-response flows).

Practical Impact

Gemini 3 Flash is a strong default when you need:

High-throughput assistants (support, ops copilots, internal tools) with tool calling
Document intelligence at scale (summaries, extraction, Q&A across long PDFs / corpora)
Multimodal pipelines (text + image/video/audio understanding) without paying “flagship Pro” prices

Use cases

Gemini 3 Flash Preview is documented as suited for coding, complex analysis, and quick answers in interactive apps. It is also described as useful for complex video analysis, data extraction, and visual Q&A.

It is documented as appropriate for agentic workflows and tool use, including multi-turn chat and collaborative coding tasks. It is also presented as useful for document analysis and deepfake detection.

Capabilities

Function calling
Streaming
Structured outputs

Gemini 3 Flash benchmarks by Artificial Analysis

See how Gemini 3 Flash compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#27 / 219207Output tokens / second Latency#192 / 2166.13Seconds to first token Humanity's Last Exam#66 / 45836.6%Score GPQA Diamond#44 / 43989.8%Score

Speed

Output tokens / second

Benchmark results

Compare 14 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Gemini 3 Flash API pricing

Gemini 3 Flash pricing in US dollars
Usage	Price	Unit
Input	$0.5	1M tokens
Output	$3	1M tokens
Cached input	$0.5	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Gemini 3 Flash vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Gemini 3 Flash	$0.5	$3
Gemini 3.5 Flash Lite	$0.3	$2.5
Gemini 3.8 Flash	$0.75	$3.75
Gemini 3.7 Flash	$0.75	$3.75
Gemini 4 Argon	$2	$10

How to use the Gemini 3 Flash API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemini-3-flash-preview",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemini-3-flash-preview",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-3-flash-preview",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Gemini 3 Flash FAQ

What is the context window of Gemini 3 Flash?

Gemini 3 Flash has a 1,000,000 tokens context window and can return up to 65,536 tokens.

What inputs and outputs does Gemini 3 Flash support?

Gemini 3 Flash takes image, text as input and returns text.

What is the model ID for Gemini 3 Flash?

Use google/gemini-3-flash-preview as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Gemini 3 Flash released?

Gemini 3 Flash became available on December 17, 2025.

How much does Gemini 3 Flash cost?

Gemini 3 Flash costs $0.5 input and $3 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Gemini 3 Flash support streaming?

Yes, Gemini 3 Flash can stream responses as they are generated.

Can Gemini 3 Flash read images?

Yes, Gemini 3 Flash accepts image input alongside text.

Who created Gemini 3 Flash?

Gemini 3 Flash was built by Google.

Can Gemini 3 Flash create images as output?

No. It accepts image and text input but only produces text output.

Start building with Gemini 3 Flash

Get API key

Gemini 3 Flash API

google/gemini-3-flash-preview

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemini-3-flash-preview",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemini-3-flash-preview",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-3-flash-preview",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Gemini 3 Flash API

Gemini 3 Flash overview

Gemini 3 Flash by Google

Gemini 3 Flash specs

Gemini 3 Flash API Overview

Technical Specifications

Performance Benchmarks

Quality Improvements

New Features & Technical Upgrades

Practical Impact

Use cases

Capabilities

Gemini 3 Flash benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Gemini 3 Flash API pricing

Gemini 3 Flash vs other models: token prices

How to use the Gemini 3 Flash API

Build with your agent

1Get your API key

2Make your first request

Related articles

Gemini 3 Flash FAQ

Start building with Gemini 3 Flash

Gemini 3 Flash API

Build with your agent

1Get your API key

2Make your first request

Gemini 3 Flash API

Gemini 3 Flash overview

Gemini 3 Flash by Google

Gemini 3 Flash specs

Gemini 3 Flash API Overview

Technical Specifications

Performance Benchmarks

Quality Improvements

New Features & Technical Upgrades

Practical Impact

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Gemini 3 Flash API pricing

Gemini 3 Flash vs other models: token prices

How to use the Gemini 3 Flash API

Build with your agent

1Get your API key

2Make your first request

Models similar to Gemini 3 Flash

Gemini 4 Argon

Gemini 3.8 Flash

Gemini 3.7 Flash

Dola-Seed 2.0 Pro

Dola-Seed 2.0 Code

Dola-Seed-2.0 Code

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Gemini 3 Flash FAQ

Start building with Gemini 3 Flash