Language models/Google/Gemini 4 Neon
Googletext1 route

Gemini 4 Neon API

Gemini 4 Neon by Google, through an OpenAI-compatible chat completions API.

gemini-4-neonGet API key

Pricing USD per million tokens

TokensPer 1M tokens
Input$4.32
Cached input$0.216
Cache write (5 min)$4.32
Cache write (1 hour)$4.32
Output$21.60

Reasoning tokens are billed as output. Each answer's usage carries cost_usd, the amount taken from your balance; a request with no answer costs $0.00.

Request

curl
curl https://api.revana.si/v1/chat/completions \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-4-neon","messages":[{"role":"user","content":"Write a haiku about routing."}]}'
Python
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.revana.si/v1", api_key=os.environ["REVANA_API_KEY"])
reply = client.chat.completions.create(
    model="gemini-4-neon",
    messages=[{"role": "user", "content": "Write a haiku about routing."}],
)
print(reply.choices[0].message.content)

Any OpenAI SDK works: set the base URL to https://api.revana.si/v1. Streaming, tools and the rest are in the chat completions docs.

Details

Model id
gemini-4-neon
Maker
Google
Endpoint
POST /v1/chat/completions
Context window
1.05M tokens
Max output
66K tokens
Streaming
Yes (server-sent events)
Routes
1

1 route

One route today. A request that gets no answer is not charged.

About the Gemini 4 Neon API

How much does the Gemini 4 Neon API cost?

Gemini 4 Neon costs $4.32 per million input tokens, $0.216 per million cached input tokens and $21.60 per million output tokens on Revana. You pay from prepaid credit for the tokens each request used, with no subscription or minimum.

How do I call Gemini 4 Neon from code?

Use any OpenAI SDK with base URL https://api.revana.si/v1 and your Revana API key, and set model to "gemini-4-neon". POST /v1/chat/completions takes the OpenAI request body, streamed or not.

What happens if a request fails?

A request that gets no answer costs nothing.

Is Gemini 4 Neon on Revana the same model?

Yes. Revana passes your request to Google's model unchanged and returns its answer in the OpenAI format, with the usage it reported and what the request cost.

More from Google

Every Gemini model and its price

Also as markdown for agents. Every language model and price: llms.json.