gemini/gemini-4-neon
Prices
As of Nov 22, 2026. Prices in euros, final amounts with no VAT shown.
| Price | € per 1M tokens |
|---|---|
| Input | 3.4172 |
| Cached | 0.1709 |
| Output | 17.0860 |
Limits
| Context | 1,048,576 tokens |
| Maximum output | 65,536 tokens |
Capabilities
| Tools | Yes |
| Images | Yes |
| Reasoning | Yes |
| Web search | Yes |
| JSON schema | Yes |
| JSON object | Yes |
| Streaming | Yes |
How to call it
Put your key in FLOWMODELS_API_KEY and this call runs as is.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.flowmodels.one/v1",
api_key=os.environ["FLOWMODELS_API_KEY"],
)
response = client.chat.completions.create(
model="gemini/gemini-4-neon",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)