Gemini 3.1 Pro Preview is the Pro-tier model of Google's Gemini 3 series, announced in February 2026 as a refinement of Gemini 3 Pro. Google describes it as built for tasks where a simple answer is not enough: complex problem solving, synthesis of large amounts of data, software engineering and agentic workflows that need precise tool use and reliable multi-step execution. Google lists a context window of up to 1M tokens. As the name says, it is still a preview release, not a stable one.
Best for
- Multi-step reasoning and data synthesis
- Agents that must call your custom tools reliably
- Interactive dashboards and code with visual output
- Comparing Pro-tier Gemini results against newer Flash models
How to call it
Point the OpenAI SDK at Jantaris and use the preview id:
from openai import OpenAI
client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
model="gemini-3.1-pro-preview",
messages=[{"role": "user", "content": "Explain the trade-offs of these three database schemas."}],
)
print(resp.choices[0].message.content)FAQ
What is the Gemini 3.1 Pro Preview price?
Jantaris charges $2.16 / $12.96 per 1M tokens. As with every model, the rate is shown before you send a request and deducted from your prepaid balance.
Is it safe to build production features on a preview model?
Be careful. Google says preview models can have tighter rate limits and may be deprecated with at least two weeks' notice. Keep the model id in a config value so you can switch quickly, and have a fallback such as gemini-3.8-flash tested in advance.
Should I choose Gemini 3.1 Pro Preview or Gemini 3.8 Flash?
For new projects Google now points developers to its latest models, including 3.8 Flash. Pick 3.1 Pro Preview if your own tests show it handles your hardest reasoning prompts better, and measure both on the same inputs in Jantaris before deciding.
How to call Gemini 3.1 Pro Preview via API
from openai import OpenAI
client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
model="gemini-3.1-pro-preview",
messages=[{"role": "user", "content": "Write a haiku about Baltic amber."}],
)
print(resp.choices[0].message.content)curl https://jantaris.com/v1/chat/completions \
-H "Authorization: Bearer $JANTARIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gemini-3.1-pro-preview", "messages": [{"role": "user", "content": "Write a haiku about Baltic amber."}]}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://jantaris.com/v1", apiKey: process.env.JANTARIS_API_KEY });
const resp = await client.chat.completions.create({
model: "gemini-3.1-pro-preview",
messages: [{ role: "user", content: "Write a haiku about Baltic amber." }],
});
console.log(resp.choices[0].message.content);