Back to Models
Google

Gemini 3.7 Flash

Available

Description

Google's high-efficiency Gemini 3.7 Flash model optimized for agentic workflows, coding, complex reasoning, and long-context multimodal intelligence with tunable thinking.

At a Glance

Key pricing and model details available for this model.

Input price

$0.75

per 1M tokens

Output price

$3.75

per 1M tokens

Context window

1M

tokens

Hallucination rate

0%

Token Pricing

Token pricing normalized to per-million-token rates.

Service tier

Set service_tier in your API request to choose throughput and pricing.

Input / 1M tokens

$0.75

Output / 1M tokens

$3.75

Cache Read / 1M tokens

$0.07

Token Pricing Details

Rates are shown per 1M tokens for easier comparison. Pass service_tier in your request to use the selected tier.

Input / 1M tokens$0.75
Input unit1M tokens
Output / 1M tokens$3.75
Output unit1M tokens
Cache Read / 1M tokens$0.07
Cache Read unit1M tokens

Feature Availability

Capabilities explicitly listed in the current payload.

LLM

Available

Yes

Vision

Available

Yes

Function calling

Available

Yes

Reasoning

Available

Yes

Service tiers

Available

Yes

Service Tiers

Available via the service_tier parameter.

default
flex
priority

Reasoning Effort Levels

low
medium
high

Supported Parameters

frequency_penalty
logit_bias
max_completion_tokens
presence_penalty
reasoning_effort
stop
temperature
top_p
tool_choice
tools
service_tier

Code Samples

Quick start with the Routeway API

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: "https://api.routeway.ai/v1",
  apiKey: "<YOUR_API_KEY>",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "gemini-3.7-flash",
    messages: [
      {
        role: "user",
        content: "Explain quantum computing in simple terms"
      }
    ]
  });

  console.log(completion.choices[0].message);
}

main();