OpenAI
GPT-5.4
From $1.00 per 1M tokens
Chat
Gemini 3.6 Flash — 1M Context, Thinking, Grounding
Gemini 3.6 Flash is Google's newest Stable Gemini 3 model, built to balance speed with intelligence across agentic and multimodal work. Gemini 3.6 Flash reads text, images, video, audio and PDF into a 1,048,576-token context window and writes up to 65,536 tokens back, with thinking, function calling and Google Search grounding all supported. On reAPI, Gemini 3.6 Flash runs at 20% below Google's published Standard rate on both input and output.
Gemini 3.6 Flashmodel
gemini-3.6-flashGemini 3.6 Flash playground
Chat models run on the api.reapi.ai gateway, which has its own console and its own key. Open the console to run Gemini 3.6 Flash through the OpenAI-compatible Chat Completions surface.
What you can build with this model
Real-world workflows and production use cases you can build and ship with this model.
Whole-document analysis without a chunking pipeline
PDF is a first-class input for Gemini 3.6 Flash, not a preprocessing step you own. Combined with the 1,048,576-token context window, that means a contract set, a research bundle or a year of reports can go into one call and come back cross-referenced. Gemini 3.6 Flash also takes images, video and audio in the same message, so a document review can include the screenshots and recordings attached to it. The practical win is that you stop maintaining a retrieval layer whose only job was working around a small context window.
Read the API docs
Agentic workflows with tools, code and grounded search
Gemini 3.6 Flash supports function calling, code execution and file search, and Google lists computer use as supported in preview. Search grounding and Grounding with Google Maps are both supported, so Gemini 3.6 Flash can answer from current sources rather than training data alone, and URL context lets you point it at a page directly. Thinking is supported, which is what carries multi-step plans between tool calls. That combination is what makes Gemini 3.6 Flash usable as the reasoning core of an agent rather than only as a text generator.
High-volume production work where the output rate decides the bill
Output tokens dominate the cost of most generative workloads, and thinking tokens count as output. Gemini 3.6 Flash carries a lower published output rate than Gemini 3.5 Flash at the same input rate, and on reAPI both dimensions land 20% under Google's published Standard rate. For summarisation fleets, classification pipelines and agent loops that run all day, that is the number that moves your monthly invoice. Gemini 3.6 Flash keeps the same million-token window while it does it, so cheaper does not mean smaller.
Pricing
Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.
| Category | Unit | Price |
|---|---|---|
| Token pricing | ||
| Input | 1M tokens | $1.2 |
| Output | 1M tokens | $6 |
Why reAPI
20% under the published Standard rate
Google publishes a Standard input and output rate for Gemini 3.6 Flash. On reAPI, Gemini 3.6 Flash bills at 80% of both — a flat 20% discount on input and on output, with no subscription underneath it and no minimum commitment. Pay-as-you-go in USD against your gateway balance.
OpenAI-compatible drop-in
Gemini 3.6 Flash is served from an OpenAI-compatible `/v1/chat/completions` endpoint. If your code already speaks that shape, adopting Gemini 3.6 Flash is a base URL, a key and a model string. The gateway also exposes a native Gemini endpoint type for this model if you prefer Google's own request format.
One key across Gemini, GPT and Claude
The same api.reapi.ai key that calls Gemini 3.6 Flash calls the GPT and Claude families too. Switching models to compare quality, or failing over when one provider has a bad hour, is a model string rather than a second integration, a second invoice and a second set of credentials.
Gemini 3.6 Flash vs Gemini 3.5 Flash
The honest version of this comparison is short: on every dimension Google publishes, Gemini 3.6 Flash and Gemini 3.5 Flash have the same surface. Same limits, same inputs, same capability list, same consumption options. Gemini 3.6 Flash is a price and positioning change, not a capability upgrade — so if you are choosing between them, the output rate and the recency are the real inputs to that decision.
Capability
Gemini 3.6 Flash on reAPI
Gemini 3.5 Flash
Google's positioning
Described as balancing speed with intelligence for agentic and multimodal tasks; the newest Stable entry in the Gemini 3 family
Described as the most intelligent model for sustained frontier performance on agentic and coding tasks
Published output rate
Lower published Standard output rate at the same input rate, and 20% under that published rate on reAPI
Higher published Standard output rate for the same input rate
Token limits
1,048,576-token input, 65,536-token output
Identical — 1,048,576-token input, 65,536-token output
Input modalities
Text, image, video, audio and PDF in; text out
Identical — text, image, video, audio and PDF in; text out
Documented capabilities
Thinking, function calling, code execution, file search, structured outputs, caching, URL context, Search and Maps grounding; computer use in preview
Identical list, item for item, including computer use in preview
Latest update
July 2026
May 2026
Comparison reflects behavior documented on Google's own model and pricing pages at the time of writing. Rates are described as relationships rather than amounts; the live numbers for Gemini 3.6 Flash are in the pricing table above.
Ship Gemini 3.6 Flash in three steps
- step 01
Create an account and key on api.reapi.ai
Sign up at api.reapi.ai, open the console and generate an API key. That one key reaches Gemini 3.6 Flash and every other model on the gateway, billed from a single balance.
Open - step 02
Point your client at the gateway
Set your base URL to api.reapi.ai and your key to the one you just created. Any client that already speaks OpenAI Chat Completions works unchanged — no SDK swap is needed to reach Gemini 3.6 Flash.
Open - step 03
Send `gemini-3.6-flash` as the model
Set the model field to `gemini-3.6-flash` and post your messages. Turn on streaming for anything interactive, and raise max tokens when you want Gemini 3.6 Flash to use more of its 65,536-token output ceiling.
Open
Frequently asked questions
Common questions about this model.
Gemini 3.6 Flash is billed pay-as-you-go in USD per token against your api.reapi.ai balance, with separate input and output rates and no subscription. Both rates sit 20% below Google's published Standard rate. Current numbers are in the pricing table on this page.
Related models
Explore more models in the same category.
DeepSeek
DeepSeek V4
From $0.140 per 1M tokens
Chat
MiniMax
MiniMax M3
From $0.600 per 1M tokens
Chat
Anthropic
Claude Opus 4.7
From $2.00 per 1M tokens
Chat
start building
Ready to ship?
Try it in the playground or grab an API key to integrate now.