Gemini 3.5 Flash: pricing, performance, and how to route requests

Route requests to
Gemini 3.5 Flash
with Merge Gateway

Apply your own routing policies, reduce token costs automatically, and see every routing decision in real time with Merge Gateway.

What Gemini 3.5 Flash costs to run

| Vendor | Input / 1M tokens | Output / 1M tokens | Zero data retention | | --- | ---: | ---: | --- | | Google | $1.50 | $9.00 | No | | Vertex AI | $1.50 | $9.00 | Yes |

Test Gemini 3.5 Flash
with Gateway’s Simulator

See a prompt's output, token spend, latency, and more with Gemini 3.5 Flash.

Route requests to Gemini 3.5 Flash in minutes

To get started in seconds, add our Gateway Implementation skill to your project, or pick your preferred SDK below. Check out our other quick start skills here.

Install the Merge Gateway SDK

Python

1$ pip install merge-gateway-sdk

Send a request

Python

1from merge_gateway import MergeGateway
2
3client = MergeGateway(api_key="YOUR_API_KEY")
4
5response = client.responses.create(
6    model="openai/gpt-5.2",
7    input=[
8        {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
9        {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
10    ],
11)
12
13print(response.output[0].content[0].text)

Try a diffrent model

Swap the model string to route to a different provider. No other code changes needed.

Anthropic

1response = client.responses.create(
2    model="anthropic/claude-sonnet-4-20250514",
3    input=[
4        {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5        {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6    ],
7)

Point to Gateway

Python

1from openai import OpenAI
2
3client = OpenAI(
4    api_key="YOUR_API_KEY",
5    base_url="https://api-gateway.merge.dev/v1/openai",
6)

Send a request

Use the standard chat.completions.create method. No provider prefix needed on the model name.

Python

1response = client.chat.completions.create(
2    model="gpt-5.2",
3    messages=[
4        {"role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5        {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6    ],
7)
8
9print(response.choices[0].message.content)

Install packages

1npm install merge-gateway-ai-sdk-provider ai

Create the provider

TypeScript

1import { createMergeGateway } from "merge-gateway-ai-sdk-provider";
2
3const gateway = createMergeGateway({
4  apiKey: "YOUR_API_KEY",
5});

Send a request

Use generateText to send a request. Model names use the provider/model format.

TypeScript

1import { generateText } from "ai";
2
3const { text } = await generateText({
4  model: gateway("openai/gpt-4o"),
5  prompt: "Explain the concept of recursion in programming with a simple set of examples.",
6});
7
8console.log(text);

If you already have @ai-sdk/openai installed, point it at Gateway with a base URL change:

TypeScript

1import { createOpenAI } from "@ai-sdk/openai";
2
3const gateway = createOpenAI({
4  apiKey: "YOUR_API_KEY",
5  baseURL: "https://api-gateway.merge.dev/v1/ai-sdk",
6});
7
8// All generateText/streamText calls work unchanged

Install the Merge Gateway SDK

Anthropic SDK

1from anthropic import Anthropic
2
3client = Anthropic(
4    api_key="YOUR_API_KEY",
5    base_url="https://api-gateway.merge.dev/v1/anthropic",
6)
7
8message = client.messages.create(
9    model="claude-sonnet-4-20250514",
10    max_tokens=1024,
11    messages=[
12        {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
13    ],
14)
15
16print(message.content[0].text)

Explore other models available in Merge Gateway

Amazon Nova 2 Lite

Amazon Nova 2 Sonic

Amazon Nova Lite

Amazon Nova Micro

Amazon Nova Premier

Amazon Nova Pro

Bland Speech v3

Claude 3.7 Sonnet

Claude 4 Opus 20250514

Claude Fable 5

Claude Fable 5.1

Claude Haiku 4.5 (20251001)

Claude Haiku 5.5

Claude Opus 4.1 (20250805)

Claude Opus 4 (20250514)

Claude Opus 4.5 (20251101)

Claude Opus 4.6

Claude Opus 4.7

Gemini 3.5 Flash FAQ

If you have additional questions about Gemini 3.5 Flash, we've addressed several more below. Keep in mind that this information was written in June, 2026 and may change over time.

Heading

What other models does Google offer?

Google maintains a lineup of proprietary Gemini models alongside open-weight Gemma models, spanning reasoning flagships to lightweight inference options. Here are some other models Google supports:

Gemini 3.1 Pro: Gemini 3.1 Pro is Google's highest-ranked model on the Artificial Analysis Intelligence Index at #5 of 150, priced at $2.00 per million input tokens and $12.00 per million output tokens, designed for workloads that require maximum reasoning depth and accept a higher cost-per-request tradeoff

Gemini 2.5 Pro: Gemini 2.5 Pro is Google's previous-generation flagship, offering extended reasoning and a 1M token context window at a price point below Gemini 3.1 Pro, suited for complex analytical workloads where the latest model generation is not required

Gemini 2.5 Flash: Gemini 2.5 Flash is a stable mid-tier model priced at $0.30 per million input tokens, delivering strong throughput and a competitive Intelligence Index score for general-purpose applications that don't need frontier reasoning

Gemini 2.5 Flash Lite: Gemini 2.5 Flash Lite is the most affordable model in Google's current lineup, priced at $0.10 per million input tokens and $0.40 per million output tokens, optimized for high-volume tasks where cost and latency matter more than peak accuracy

Gemma 4 31B: Gemma 4 31B is an open-weight model available under the Apache 2.0 license at google/gemma-4-31b-it on Hugging Face, supporting a 256K token context window and multimodal inputs for teams that need self-hosted inference or on-premises deployment

How does Gemini 3.5 Flash differ from Google's other models?

Gemini 3.5 Flash is Google's current stable frontier model, balancing high Intelligence Index performance with faster output speed than Gemini 3.1 Pro and a lower price point.

Intelligence Index: Gemini 3.5 Flash scores 55 on the Artificial Analysis Intelligence Index, ranking #9 of 150 evaluated models. Gemini 3.1 Pro scores 57 at #5, placing Gemini 3.5 Flash just below the top of the Google lineup while outranking Gemini 2.5 Pro and all Flash-Lite models

Pricing: Input costs $1.50 per million tokens and output costs $9.00 per million tokens. This is 25% cheaper on input and 25% cheaper on output than Gemini 3.1 Pro, and significantly above Gemini 2.5 Flash at $0.30 input. Gemini 3.5 Flash occupies the high-performance tier without the full flagship price

Speed: Gemini 3.5 Flash outputs 163.1 tokens per second, which is faster than Gemini 3.1 Pro at 133.7 tokens per second. This makes Gemini 3.5 Flash better suited for applications where response time matters alongside quality

Capabilities: Gemini 3.5 Flash is a reasoning model that accepts text, image, speech, and video inputs and produces text output. It shares multimodal support with Gemini 3.1 Pro and uses extended thinking, though its Intelligence Index score reflects a slight quality tradeoff relative to the Pro tier

Context window: Supports a 1M token context window, matching Gemini 3.1 Pro and Gemini 2.5 Pro, making it fully capable for long-document retrieval, large codebase analysis, and extended multi-turn sessions

Gemini 3.5 Flash is the right choice when you need near-flagship reasoning quality with faster throughput and a lower per-request cost, such as in production agentic pipelines, coding assistants, and complex document workflows

What models should I consider using alongside Gemini 3.5 Flash?

No single model is optimal for every task. Here are models worth pairing with Gemini 3.5 Flash depending on what your product needs:

Gemini 3.1 Pro: For the hardest reasoning tasks in your pipeline, such as multi-step scientific analysis or formal code verification, route to Gemini 3.1 Pro to get the top-ranked Google model for requests where the incremental quality gain justifies the higher cost

Gemini 2.5 Flash Lite: For high-volume classification, extraction, or preprocessing steps that feed into a Gemini 3.5 Flash call, Gemini 2.5 Flash Lite at $0.10 per million input tokens handles the groundwork so Gemini 3.5 Flash only processes requests that need its full capability

Claude Sonnet 4 (Anthropic): For instruction-following, structured data extraction, and long-form writing tasks where a cross-provider comparison is useful, Claude Sonnet 4 provides an alternative mid-to-high tier reasoning model to A/B test against Gemini 3.5 Flash on your specific workload

o4-mini (OpenAI): For math-heavy reasoning and STEM tasks where a cost-efficient reasoning model from a second provider adds redundancy, o4-mini offers a competitive benchmark alternative to Gemini 3.5 Flash at a different price point

Gemma 4 31B: For teams with data residency requirements or self-hosting needs, Gemma 4 31B provides an open-weight multimodal alternative for tasks where sending data to a cloud API is not acceptable

What are the challenges of using Gemini 3.5 Flash in my product?

Like any production LLM, Gemini 3.5 Flash comes with tradeoffs worth planning for:

Cost at scale: At $1.50 per million input tokens and $9.00 per million output tokens, Gemini 3.5 Flash is priced at the high tier of Google's lineup. As request volume grows, token costs compound quickly without active cost controls, particularly given the model's tendency toward verbose completions

Provider dependency: Routing all traffic to Google's API means any quota restriction, regional outage, or model version change directly affects every workload relying on Gemini 3.5 Flash. A single-provider setup has no automatic fallback when Google's API becomes unavailable

Output verbosity: Gemini 3.5 Flash generated 73M output tokens during the Artificial Analysis Intelligence Index evaluation, the highest verbosity figure noted for this model tier. At $9.00 per million output tokens, lengthy completions make the effective cost per task higher than headline pricing suggests, particularly for open-ended generation tasks

Latency for interactive use cases: Time to first token averages approximately 21 seconds, which reflects the extended thinking the model performs before generating a response. Real-time applications like live chat or autocomplete need controls to limit reasoning depth or use a faster fallback model for latency-sensitive paths

Rate limits and quota management: Frontier reasoning models at this tier typically have tighter rate limits than mid-tier or flash-lite models. Traffic spikes without quota management can lead to 429 errors that degrade user experience without a fallback in place

Why should I use Merge Gateway to route LLM requests with Gemini 3.5 Flash and every other model?

Using Gemini 3.5 Flash through Merge Gateway gives you access to the model itself and the infrastructure layer around it:

One API, every provider: Access Gemini 3.5 Flash and every other major LLM through a single endpoint and API key. Change providers by swapping the model string, with no application code changes required

Intelligent routing and automatic failover: Merge routes around Google outages automatically. Routing policies based on cost, latency, or quality can reduce spend by 40-60% without touching your application code, which is especially useful when pairing Gemini 3.5 Flash with cheaper models for lower-complexity requests

Cost governance: Set hard or soft project budgets so Gemini 3.5 Flash spend stays within plan. Every request is attributed to a model, project, and tag in a unified billing dashboard across all providers

Build Your Own Router: Define what "best" means for your traffic by selecting from curated ML benchmarks or adding your own eval scores. The router scores each available model against your weights and picks the winner per request, with a plain-language explanation of every decision

Security and compliance controls: Apply DLP rules and prompt injection protection before every request reaches Google. Enforce per-project model and region policies without adding that logic to your application

How can I start routing requests to Gemini 3.5 Flash via Merge Gateway?

Getting Gemini 3.5 Flash running through Merge Gateway takes a few minutes:

1. Create an account and get your API key from the dashboard.

2. Install the Merge Gateway SDK: run pip install merge-gateway-sdk (Python) or npm install merge-gateway-sdk (Node). Alternatively, if you're already using the OpenAI SDK, set base_url = "https://api-gateway.merge.dev/v1/openai" and your existing code works as-is.

3. Make your first request using the provider/model format. For Gemini 3.5 Flash, the model string is google/gemini-3.5-flash. Swap the model string to route to any other provider without changing anything else.

4. Configure a routing policy in the dashboard to set failover behavior, cost limits, and optimization strategy. Your first policy can be as simple as naming Gemini 3.5 Flash as primary with one fallback.

Full setup instructions and SDK references are in the Merge Gateway docs.