Gemini 3 Flash API

US Google | released 2026-05

Gemini 3 Flash is the speed-optimized Gemini model, offering strong quality at low latency and cost. Ideal for real-time assistants, classification, and high-throughput tasks that still need multimodal input.

ImageVideoAudioFastTool UseJSON Mode

Pricing (official list, per 1M tokens)

Input

$0.50/M

Output

$3.00/M

Specifications

Context window1048.576K tokens Max output65.536K tokens Input modalitiesImage, Video, Audio StreamingYes APIOpenAI-compatible

How to use Gemini 3 Flash

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-3-flash",
    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-3-flash","messages":[{"role":"user","content":"Hello!"}]}'