Start free trial

Google: Gemini 3.1 Pro Preview

google/gemini-3-1-pro-preview
CompareAPITry this model

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.

Modalities
In / out per 1M$2.00 / $12
Context1M
ReleasedFeb 19, 2026

Providers

6 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Google AI Studio$1.00$6.00$0.104.96s128 tps99.94%
Google AI Studio$2.00$12$0.206.54s103 tps99.79%
Google AI Studio$3.60$22$0.364.64s104 tps99.2%
Google Vertexglobal$2.00$12$0.203.21s79 tps99.17%
Google Vertexglobal$3.60$22$0.366.97s27 tps98.54%
Google Vertexglobal$1.00$6.00$0.1097.30s13 tps84.23%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Gemini 3.1 Pro Preview in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Gemini 3.1 Pro Preview costs pay-as-you-go elsewhere, not what you pay here.

Input
$2.00
per 1M tokens
Output
$12
per 1M tokens
Cache read
$0.20
per 1M cached tokens
Included in every pass
Gemini 3.1 Pro Preview is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s50.0s100.0s150.0s200.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Google AI Studio Google AI Studio Google Vertex (global) Google Vertex (global) Google Vertex (global) Google AI Studio
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Google AI Studio Google AI Studio Google Vertex (global) Google Vertex (global) Google Vertex (global) Google AI Studio

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.8%
Oct 16, 12:00 PMNow
Availability over the last 24 hoursAvailability 99.81%
100% 97% 93% 90%
Oct 18, 12:10 PMNow

Apps

Tools that most often run Gemini 3.1 Pro Preview, by tokens this week.

Claude CodeCli Agent · 68.9% of tokens92.8BSITE1239.7% of tokens13.0BHermes AgentPersonal Agent · 7.8% of tokens10.5BJanitor AIRoleplay · 7.4% of tokens9.9BSillyTavernRoleplay · 6.2% of tokens8.4B

Activity

883.0B tokens processed market-wide in the last month.

020.0B40.0B60.0B80.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens

FAQ

Which model id do I use for Gemini 3.1 Pro Preview?
google/gemini-3.1-pro-preview. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Gemini 3.1 Pro Preview hold?
1,048,576 tokens per request, of which up to 65,536 can be the response.
What can it accept and return?
Input: audio, file, image, text, video. Output: text.
What does Gemini 3.1 Pro Preview cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $2.00 per 1M input tokens and $12 per 1M output tokens.
Who built Gemini 3.1 Pro Preview?
Google, in the Gemini family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion