Google

Gemini 2.5 Flash Live API

US Google
Try in Playground → Get API key

Gemini 2.5 Flash Live is a fast, cost-efficient model from Google. It offers multimodal vision. Available through the MeshTok unified API.

ImageAudioFastTool Use

Pricing (official list, per 1M tokens)

Input
$0.10/M
Output
$0.40/M

Specifications

Context window1000K tokens Input modalitiesImage, Audio StreamingYes APIOpenAI-compatible

How to use Gemini 2.5 Flash Live

Drop-in OpenAI replacement. Change only the base_url and model.

# Python -pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://meshtok.com/v1",
    api_key="sk-your-MeshTok-key",
)

resp = client.chat.completions.create(
    model="google/gemini-2.5-flash-live",
    messages=[{"role":"user","content":"Hello!"}],
)
print(resp.choices[0].message.content)
# cURL
curl https://meshtok.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-MeshTok-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-2.5-flash-live","messages":[{"role":"user","content":"Hello!"}]}'

Related models

Other models you might consider.