Gemini 3.5 Flash
Google's high-performance dialogue model is fast and highly accurate, ideal for text generation, Q&A, and multi-turn conversations.
Use cases
gemini-3.5-flash prototyping · gemini-3.5-flash production workflows
Input
Text, image
Output
Text
Billing
Per token
Start a conversation
Type a message below to begin
Sign up to get $0.5 in free credits — about 20 free images
Pricing details
Transparent usage-based pricing with no hidden fees.
Detailed Pricing
Usage-based pricing breakdown
| Spec | Price | Official | Savings |
|---|---|---|---|
| Input/1M tokens | 1.2 Credits≈$1.2 | 1.5 Credits | -20% |
| Output/1M tokens | 6 Credits≈$6 | 7.5 Credits | -20% |
| Cache Read/1M tokens | 0.12 Credits≈$0.12 | 0.15 Credits | -20% |
Billing Rules
- Output price varies by model, resolution, quality, duration, or token usage.
- Uploaded reference files may be charged separately when supported.
- Add-on capabilities such as web search or image search may be billed per request.
- Token-based models are billed by input and output tokens.
- If the primary route is unavailable, Velokey may automatically switch to a stable fallback route when possible.
- Usage is pay-as-you-go with transparent credit deduction.
* Final cost depends on the generated result.
Related models
Explore other models in the same family.
GoogleSave 20%Gemini 3.1 Pro Preview
Gemini 3.1 Pro delivers reasoning with unprecedented depth, top-tier agentic coding, and multimodal understanding of text, image, audio, video and PDF over a 1M-token context.
- GoogleSave 20%
Gemini 3 Pro Preview
Gemini 3 Pro is Google's state-of-the-art multimodal reasoning model with agentic coding, a 1M-token context, and a Deep Think mode for the hardest problems.
- GoogleSave 20%
Gemini 3.1 Flash Lite Preview
Gemini 3.1 Flash is Google's most cost-efficient model in the 3 series, with flexible reasoning, multimodal input and a 1M-token context for high-volume, low-latency tasks.
- GoogleSave 20%
Gemini 3 Flash Preview
Gemini 3 Flash brings Pro-grade reasoning at Flash-level latency and cost — strong coding (SWE-bench 78%), 3x faster than 2.5 Pro, and multimodal understanding.
Affordable Google Gemini 3.5 Flash API
Access Google DeepMind's Gemini 3.5 Flash on Velokey — frontier performance for agents and coding at Flash-level latency and scale, with multimodal understanding, a 1M-token context, a unified endpoint, and below-list pricing.
Meet Gemini 3.5 Flash and its API access
Gemini 3.5 Flash is Google DeepMind's preview model built for frontier performance across agents and coding. It delivers advanced reasoning at Flash-level latency and scale, with coding and reasoning quality close to Gemini Pro while preserving Flash's speed and cost. It excels at agentic workflows — multi-step tasks with iterative loops and agent coordination — and is natively multimodal, processing text, images, video, audio, and PDFs. It ships with a 1M-token input context (64K output) and a knowledge cutoff of January 2025. Velokey provides an affordable, easy-to-integrate Gemini 3.5 Flash API: a unified chat endpoint, one API key, a clear request flow, and below-list pricing for production systems, agent pipelines, and automation tools.
Frontier agentic performance at Flash latency
Best for frontier performance across agents and coding — advanced reasoning delivered at Flash-level latency and scale, with quality close to Gemini Pro. On MCP Atlas (multi-step workflows) it reaches 83.6% versus 62.0% for Gemini 3 Flash, and 57.9% versus 42.6% on Finance Agent v2.
View Documentation →
Strong agentic coding
Excels at agentic coding and multi-step tasks with iterative loops and agent coordination, scoring 76.2% on Terminal-bench 2.1 versus 58.0% for Gemini 3 Flash — a large jump in real agentic coding.
View Documentation →
Native multimodal understanding
Processes text, images, video, audio, and PDFs together, so a single request can reason over mixed media — fit for document understanding, media analysis, and multimodal assistants.
View Documentation →
1M-token long-context understanding
Handles up to 1M input tokens with 64K output, reasoning coherently across entire codebases, long documents, and large archives in a single call, with a knowledge cutoff of January 2025.
View Documentation →
How to call the Gemini 3.5 Flash API on Velokey
Get started with just a few steps.
Sign up and get an API Key
Sign in to the Velokey console to generate an API Key that authenticates every request sent to Gemini 3.5 Flash.
Configure request parameters
Set model to gemini-3-5-flash and submit messages. Attach text, images, video, audio, or PDFs for multimodal input, and use the 1M-token context for long inputs.
Integrate and start calling
Send requests to Velokey's unified endpoint to power agents, coding assistants, and automation, with credits and usage managed in one console.
Real-world use cases for Gemini 3.5 Flash
From everyday tasks to agentic coding, covering many high-throughput scenarios.
Everyday tasks at scale
Flash-level latency and cost make it fit for high-volume everyday tasks like chat, drafting, and Q&A without sacrificing quality.
Agentic coding
Strong on Terminal-bench 2.1 (76.2%) — fit for coding agents that run iterative loops across a terminal and codebase.
Advanced reasoning
Reasoning quality close to Gemini Pro — fit for multi-step problem solving and analysis that needs frontier-level thinking.
Multimodal understanding
Processes text, images, video, audio, and PDFs together — fit for media analysis, document parsing, and multimodal assistants.
Long-context understanding
A 1M-token input context fits entire codebases, long reports, and large archives into a single request for coherent reasoning.
Multi-step agent workflows
Strong on MCP Atlas (83.6%) and Finance Agent v2 (57.9%) — fit for agents that coordinate tools across long multi-step workflows.
Why choose Velokey for Gemini 3.5 Flash
Discount on list price
Call Gemini 3.5 Flash at a lower price on Velokey — pay-as-you-go with no forced subscription, reducing upfront cost.
Unified API interface
One API Key accesses Gemini 3.5 Flash and other models — no juggling multiple accounts and keys, simplifying integration.
Complete docs and examples
Endpoint references, parameter details, and multimodal examples help you wire up agents, coding, and long-context calls quickly.
Stable and highly available
Automatic failover and stable fallback routes maintain availability when the primary route is down, keeping production reliable.
API Reference
Complete API call examples and parameter descriptions
Endpoint
https://api.velokey.ai/v1beta/models/{model}:generateContentAuthentication
Bearer YOUR_API_KEYRequest Example
curl https://api.velokey.ai/v1beta/models/{model}:generateContent \
-X POST \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.5-flash",
"messages": [{"role": "user", "content": "Hello!"}],
"temperature": 0.7
}'Response Example
{
"id": "req_abc123",
"model": "gemini-3.5-flash",
"created": 1234567890,
"data": { ... }
}gemini-3.5-flash API FAQ
What is the gemini-3.5-flash API?
gemini-3.5-flash is available through Velokey as a chat model. Set model to gemini-3-5-flash and use the family-specific endpoint.
Which parameters does gemini-3.5-flash use?
The playground shows the main fields for gemini-3.5-flash, including the model id and the most important generation parameters.
How is gemini-3.5-flash billed?
Pricing is shown on this page when available, and credits are managed from one Velokey account.
Who should use gemini-3.5-flash?
It fits teams that want to test, compare, and ship AI capabilities through a unified API.
Start building with Gemini 3.5 Flash today
Use one API key to access low-cost, stable AI models through Velokey.