Gemini 3.1 Pro Preview

gemini-3.1-pro-preview by Google Cloud Released February 20, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$2 / 1M
Output from
$12 / 1M
Cached input from
$0.2 / 1M
Context window
1.05M
Endpoints
2
from 2 providers
Regions
Monde

About Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview est le modèle de raisonnement de pointe de Google, qui offre des performances accrues en matière d'ingénierie logicielle, une fiabilité améliorée des agents et une utilisation plus efficace des tokens dans le cadre de workflows complexes.

Gemini 3.1 Pro Preview est un modèle conversationnel développé par Google Cloud, disponible sur Eden AI via 2 endpoints chez 2 fournisseurs, à partir de 2 $ par million de tokens en entrée et 12 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

2 endpoints from 2 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. Au-delà de 200K tokens : 4 $ en entrée / 18 $ en sortie par 1M.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Google CloudOfficial−%google/gemini-3.1-pro-preview
Monde
1.05M
$2$2
$12
$0.2
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/gemini-3.1-pro-preview
Monde
1.05M
$2$2
$12
$0.2
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
12.63 s
Google Cloud
Lowest latency
22.32 s
Google Cloud
Highest throughput
100.62 tok/s
Google Cloud
Best availability
99.56%
Google Cloud
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Google Cloud
12.63 s
22.32 s
53.91 s
100.62 tok/s
99.56%
17%
0.21%
0%
Google Cloud
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Gemini 3.1 Pro Preview with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about Gemini 3.1 Pro Preview

On Eden AI, prices for this model start at $2 per million input tokens and $12 per million output tokens. Prices differ by endpoint; the providers table lists each one. Au-delà de 200K tokens : 4 $ en entrée / 18 $ en sortie par 1M.

Up to 1.05M tokens, depending on the endpoint.

2 endpoints from 2 providers, available in: Monde. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 12.63 s (Google Cloud) and the highest throughput was 100.62 tokens per second (Google Cloud).