PL Log inOpen Studio
CatalogVideo36Image31Audio5Chat & code27New AI modelsCost calculatorAI agents

Chat & code Google · 2026-11

Gemini 4 Neon API

Google's newest Gemini 4 for coding and agents - fast, with a 1M-token context

Input$3.24per 1M tokens
Output$16.20per 1M tokens
Cached input$0.162per 1M tokens

1,000 chatbot replies$11.341,500 input + 400 output tokens each

Prompt caching works through the API: repeated context is billed at the cached rate. Failed requests cost nothing.

Compare with other chat models →

Gemini 4 Neon is a model from Google's Gemini 4 series, released on November 18, 2026. Google built it on top of Gemini 4 Carbon for fast coding and agentic work - repositories, the terminal, multi-step tasks with tools. It has one shared 1,048,576-token window for input, thinking and output. Thinking depth is set by level (low, medium - the default, high). It supports tool calls and JSON schema output. It answers with text. In Jantaris you call it with the same OpenAI SDK as every other model, without a separate Google account.

A single answer is capped at 32,768 tokens without streaming and 65,536 with streaming, and thinking counts toward that cap. For long answers set stream: true.

The same series has Gemini 4 Hydrogen for cheap, high-volume work, Gemini 4 Argon and Gemini 4 Carbon. Neon has the highest token price of them, so pick it where speed on code and agent work matters more than the lowest price.

Best for

  • Writing and fixing code in large repositories
  • Tool-using agents, terminal work, many steps in a row
  • Extracting data from long documents to JSON
  • Head-to-head tests with Gemini 4 Carbon, Claude Sonnet 5.5 and GPT-6.2 Sol on your own tasks

How to call it

python
from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="gemini-4-neon",
    stream=True,
    reasoning_effort="medium",
    messages=[{"role": "user", "content": "Write tests for this function and list the edge cases."}],
)
for chunk in resp:
    print(chunk.choices[0].delta.content or "", end="")

FAQ

What is the Gemini 4 Neon API price?

$3.24 / $16.20 per 1M tokens. You pay from one balance, only for the tokens you use.

How is it different from Gemini 4 Carbon?

Neon is built on Gemini 4 Carbon and tuned for fast coding and agent work. The window is the same, the token price is higher. For longer, slower reasoning tasks compare both on your own data.

How long can an answer be?

Up to 32,768 tokens without streaming and 65,536 with streaming, thinking included.

Does Neon generate images or audio?

No, it answers with text only.

How to call Gemini 4 Neon via API

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="gemini-4-neon",
    messages=[{"role": "user", "content": "Write a haiku about Baltic amber."}],
)
print(resp.choices[0].message.content)