KovAPIKovAPI
Chat ● Degraded Service status →

Gemini 4 Neon

Beta ⧉
gemini-4-neon

Gemini 4 Neon is the mid-tier Gemini 4 model Google released on November 18, 2026, listed at $3 input and $15 output per million tokens. It sits between Hydrogen and Carbon, and Google names it as the upgrade target for Gemini 4 Argon and Gemini 3.1 Pro. It is available in Beta for text chat and reasoning with three thinking levels, Low, Medium and High; High is the default, as on Google's own API, and thinking tokens bill at the output rate. The official 1,048,576-token context is shared by input and output, with up to 65,536 output tokens per response by default. Image input, tool calling and JSON structured output are supported.

BetaLow / Medium / High1M contextOpenAI compatible

Live Test · Playground

Try out Gemini 4 Neon right here (available after login).

Input

Advanced
Web search
Memory · multi-turn

Conversation

Start a conversationType a message below to begin

About Gemini 4 Neon

Gemini 4 Neon is the mid-tier Gemini 4 model Google released on November 18, 2026, available on KovAPI in Beta for text chat and reasoning through the OpenAI-compatible API. Its list price is $3 input and $15 output per million tokens. It sits between Hydrogen and Carbon, and Google names it as the upgrade target for Gemini 4 Argon and Gemini 3.1 Pro. Thinking comes in three levels, Low, Medium and High; High is the default and thinking tokens bill at the output rate. The official 1,048,576-token context is shared by input and output, with up to 65,536 output tokens per response by default. Image input, tool calling and JSON structured output are supported.

Use cases

Everyday coding and code review

Writing functions, fixing bugs, reading unfamiliar code and adding tests: Neon is the model Google points Argon and 3.1 Pro users to for coding and enterprise reasoning.

Multi-step reasoning

Math, logic and trade-off questions that need thinking before answering run at High by default; drop to Low or Medium for simple prompts to save output tokens.

Long documents and long conversations

The million-token context holds a whole manual, a long contract or a very long chat history, so you can ask directly without building a retrieval step first.

Tool calling and structured output

Function calling and json_schema both work, which suits decision steps in agents, batch extraction and classification.

How to choose

Pick Neon when you need stronger reasoning and coding than Hydrogen without paying Carbon prices. Pick Gemini 4 Hydrogen for budget-first, high-volume work, and Gemini 3.8 Flash for faster, cheaper simple jobs. If you use Gemini 4 Argon today, Google recommends moving to Neon.

FAQ

How do I set the thinking level?
Send reasoning_effort="low", "medium" or "high" in the OpenAI-compatible request, or pick it in Advanced settings on this page. Default: high, as on Google's API. All levels use the same token rates; more thinking consumes more output tokens.
Is xhigh supported?
Google's Neon has an xhigh level, but it is not available here yet: sending xhigh returns 400 and nothing is charged. We will update this page when it opens.
How is it different from Gemini 4 Argon and Hydrogen?
Neon lists at $3 / $15, above Hydrogen ($1.50 / $7.50) with stronger reasoning, and Google names Neon as the upgrade target for Argon and 3.1 Pro. Choose Hydrogen when cost matters most and Neon for stronger reasoning and coding.
How large is the context?
The official window is 1,048,576 tokens shared by input and output, with up to 65,536 output tokens per response by default. Split very long jobs during Beta.
Does it support images, tool calling and JSON output?
Yes. Send images in the message, or define tools in the OpenAI format and get standard tool_calls back; json_schema structured output works too.
What does Beta mean?
During Beta the upstream capacity can vary. Failed calls are never billed and can be resubmitted as they are. We drop the Beta label once features and prices are stable.

Related Models

Explore other models you can integrate.

View all →