Gemini 3 API — pricing, availability, and the live way to call Gemini today

Gemini 3 is Google's flagship model family — Gemini 3 Pro, Gemini 3.1 Pro and Gemini 3 Flash — natively multimodal, 1M+ token context, chain-of-thought reasoning. This guide covers what the Gemini 3 API costs at Google's list, its status on Kunavo, and how to run the same workloads today on Gemini 2.5 through one OpenAI-compatible endpoint.

Gemini 3 API pricing

Google's official list rates for the family, next to the live Gemini 2.5 rates on Kunavo (about 70% under Google's 2.5 list):

Full 2.5-family rates and worked cost examples are in the Gemini API pricing guide.

Gemini 3.6 Flash — what changed

Gemini 3.6 Flash is the newest member of the family and the one worth understanding before you budget for it. Google lists it at $1.50 input / $7.50 output per 1M tokens — the same input price as Gemini 3.5 Flash with output cut about 17% — and pitches it at long-horizon agent work, where it claims to cut token cost substantially on multi-step engineering tasks.

The number that actually decides your bill is not on the price list: 3.6 Flash thinks by default, and the thinking dominates the output meter. In our testing a one-sentence factual answer spent roughly 120–140 reasoning tokens to produce 7 visible output tokens. Reasoning tokens bill at the output rate, so the honest cost of a short 3.6 Flash answer is closer to 150 output tokens than to 7 — roughly 20× the naive estimate. Two practical consequences:

• Do not set a small max_tokens. Anything under ~150 gets consumed by reasoning before the model emits an answer, and you receive a truncated fragment while still paying for the thinking.
• Budget on reasoning, not on visible output. For short, high-volume calls a non-thinking Flash tier is usually cheaper in practice, even at a higher sticker price per token.

Gemini 3.6 Flash is live on Kunavo at $1.05 / $5.25 per 1M — about 30% under Google's $1.50 / $7.50 list, on the same OpenAI-compatible endpoint as everything else, with no Google Cloud project required. It is the first Gemini 3 model we can serve; the Pro tiers remain unavailable. Call it as gemini-3-6-flash.

Call Gemini on Kunavo today

Kunavo fronts Gemini behind the OpenAI-compatible /v1/chat/completions endpoint — keep the OpenAI SDK, change base_url, no Google Cloud project:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["KUNAVO_API_KEY"],
    base_url="https://api.kunavo.com/v1",
)

# Gemini 3.6 Flash is live. Mind the max_tokens: 3.6 Flash reasons by default
# and reasoning bills as output, so a small cap gets spent thinking and returns
# a truncated answer.
resp = client.chat.completions.create(
    model="gemini-3-6-flash",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Summarize this contract in 5 bullets."}],
)
print(resp.choices[0].message.content)

Getting a key takes a minute — see the Gemini API key guide. The same sk-kn- key also reaches Claude, GPT, Nano Banana image and Veo 3 video.

Gemini 3 vs Gemini 2.5 — should you wait?

• Long-context and reasoning workloads — Gemini 2.5 Pro already carries 1M-token context and strong chain-of-thought; it's the pragmatic default while 3 stabilizes.
• High-volume, latency-sensitive calls — Gemini 2.5 Flash at $0.09 in / $0.75 out is the cost-efficiency play; Gemini 3 Flash will slot into the same tier.
• Building for the upgrade — code against the OpenAI-compatible shape and treat the model string as config; the Gemini 3 slugs land behind the same endpoint.

FAQ