Gemini 3.1 Pro Preview API - Google Pro tier per token

Name: Gemini 3.1 Pro Preview API
Brand: Google
Price: 2.1600 USD
Availability: InStock

Gemini 3.1 Pro Preview is the Gemini to try when a short, direct answer will not do: problems that need several steps of reasoning, pulling a conclusion out of a lot of data, software work and agents that must call your tools exactly right. Google announced it in February 2026 as a refined Gemini 3 Pro and lists a context window of up to 1M tokens.

The name is honest: this is a preview, not a stable release, so plan for change.

What you can use it for

Reasoning chains and summaries that merge many sources
Agents that depend on correct calls to your own functions
Interactive dashboards and code that renders something visual
Benchmarks of Pro-tier Gemini against newer Flash releases

Settings and limits

Context window: up to 1M tokens, according to Google.
Model id on Kadraris: gemini-3.1-pro-preview, called through /v1/chat/completions.
Google warns that preview models may have tighter rate limits and can be retired with at least two weeks' notice.
Keep the model id in a config value rather than in code, so a swap takes one line.
Test a fallback such as Gemini 3.6 Flash before you need it.

Example request

python

from openai import OpenAI

client = OpenAI(
    base_url="https://kadraris.com/v1",
    api_key="sk-kd-...",
)
resp = client.chat.completions.create(
    model="gemini-3.1-pro-preview",
    messages=[{"role": "user",
               "content": "Compare these two pricing "
                          "models and pick one."}],
)
print(resp.choices[0].message.content)

Paste the data you want weighed under the instruction and state the criteria that matter to you.

Questions

What will Gemini 3.1 Pro Preview cost me?

$2.16 / $12.96 per 1M tokens, taken from your prepaid balance. A request that fails is not charged.

Pro Preview or a newer Flash?

Flash models cost less per token. Gemini 3.6 Flash caps replies at 8,192 tokens, while gemini-3.8-flash allows much longer ones. Run your hardest prompts on both with the same key and keep the cheaper one if it holds up. The 3.8 Flash vs 3.1 Pro Preview page compares them.

Do I need a Google Cloud account?

No. The Kadraris key and the OpenAI SDK are enough.

Gemini 3.1 Pro Preview in your code

from openai import OpenAI

client = OpenAI(base_url="https://kadraris.com/v1", api_key="sk-kd-...")
resp = client.chat.completions.create(
    model="gemini-3.1-pro-preview",
    messages=[{"role": "user", "content": "Suggest three opening shots for a short film about a cafe."}],
)
print(resp.choices[0].message.content)

curl https://kadraris.com/v1/chat/completions \
  -H "Authorization: Bearer $KADRARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gemini-3.1-pro-preview", "messages": [{"role": "user", "content": "Suggest three opening shots for a short film about a cafe."}]}'

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://kadraris.com/v1", apiKey: process.env.KADRARIS_API_KEY });
const resp = await client.chat.completions.create({
  model: "gemini-3.1-pro-preview",
  messages: [{ role: "user", content: "Suggest three opening shots for a short film about a cafe." }],
});
console.log(resp.choices[0].message.content);