gemini-2.5-flash-lite latest preview version
Pricing
Input Modalities
- Text
- Vision
- Audio
- Video
Output Modalities
- Text
Capabilities
- Tools
- Tool calling
- Structured outputs
Try this model
Python
| Pricing | Cache Read | Input Audio | Input Audio Cached | Web Search | Cache Storage |
|---|---|---|---|---|---|
Pricing | Cache Read | Input Audio | Input Audio Cached | Web Search | Cache Storage |
$0.1$0.4 | $0.025/M tokens | $0.3/M tokens | $0.125/M tokens | $0.035/request | $1/h/M tokens |
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AIHUBMIX_API_KEY"],
base_url="https://shkq.org/v1",
)
response = client.chat.completions.create(
model="gemini-2.5-flash-lite-preview",
messages=[
{
"role": "user",
"content": "Hello, how are you?"
}
],
max_tokens=1024,
stream=False,
)
print(response.choices[0].message.content)0.04$/image ;2.49m/tokens
Aihubmix supports the gemini-2.5-flash-image model (known on social media as nano-banana); you can add the extra parameter modalities=["text", "image"] via the OpenAI-compatible chat interface. This model allows adjustment of the generated image’s aspect ratio through parameters, but requires using the native Gemini SDK.
© 2023 - 2026 AIHubMix, LLC