Gemini 3.1 Pro Preview
Gemini 3.1 Pro is Google DeepMind's model built for deep reasoning and advanced agentic coding, with multimodal input and 1M-token context. Access it through Velokey's unified endpoint with below-list pricing.
Use cases
Agentic applications & advanced coding · Long-context document understanding
Input
Text, image
Output
Text
Billing
Per token
Start a conversation
Type a message below to begin
Sign up to get $0.5 in free credits — about 20 free images
Pricing details
Transparent usage-based pricing with no hidden fees.
Detailed Pricing
Usage-based pricing breakdown
| Spec | Price | Official | Savings |
|---|---|---|---|
| Input/1M tokens | 1.6 Credits≈$1.6 | 2 Credits | -20% |
| Output/1M tokens | 9.6 Credits≈$9.6 | 12 Credits | -20% |
| Cache Read/1M tokens | 0.16 Credits≈$0.16 | 0.2 Credits | -20% |
Billing Rules
- Output price varies by model, resolution, quality, duration, or token usage.
- Uploaded reference files may be charged separately when supported.
- Add-on capabilities such as web search or image search may be billed per request.
- Token-based models are billed by input and output tokens.
- If the primary route is unavailable, Velokey may automatically switch to a stable fallback route when possible.
- Usage is pay-as-you-go with transparent credit deduction.
* Final cost depends on the generated result.
Related models
Explore other models in the same family.
GoogleSave 20%Gemini 3 Pro Preview
Gemini 3 Pro is Google's state-of-the-art multimodal reasoning model with agentic coding, a 1M-token context, and a Deep Think mode for the hardest problems.
- GoogleSave 20%
Gemini 3.1 Flash Lite Preview
Gemini 3.1 Flash is Google's most cost-efficient model in the 3 series, with flexible reasoning, multimodal input and a 1M-token context for high-volume, low-latency tasks.
- GoogleSave 20%
Gemini 3 Flash Preview
Gemini 3 Flash brings Pro-grade reasoning at Flash-level latency and cost — strong coding (SWE-bench 78%), 3x faster than 2.5 Pro, and multimodal understanding.
- GoogleSave 20%
Gemini 3.5 Flash
Google's high-performance dialogue model is fast and highly accurate, ideal for text generation, Q&A, and multi-turn conversations.
Affordable Gemini 3.1 Pro API
Access Google DeepMind's Gemini 3.1 Pro on Velokey — deep, nuanced reasoning, advanced agentic coding, and 1M-token multimodal understanding, with a unified endpoint and below-list pricing for production apps.
Meet Gemini 3.1 Pro and its API access
Gemini 3.1 Pro is Google DeepMind's preview model built for reasoning with unprecedented depth and nuance, advanced standard and agentic coding, and multimodal understanding across text, images, video, audio, and PDF to text output. It ships with a 1M-token input context and 64K max output, and scores 44.4% on Humanity's Last Exam (no tools), 94.3% on GPQA Diamond, and 80.6% on SWE-Bench Verified. Velokey provides an affordable, easy-to-integrate Gemini 3.1 Pro API: a unified endpoint, one API key, a clear request flow, and below-list pricing for production systems, agent pipelines, and automation tools.
Reasoning with unprecedented depth and nuance
Works through hard multi-step problems with unprecedented depth and nuance, scoring 44.4% on Humanity's Last Exam without tools and 94.3% on GPQA Diamond — fit for demanding scientific and analytical work.
View Documentation →
Advanced agentic coding
Handles advanced standard and agentic coding, reaching 80.6% on SWE-Bench Verified and 2887 Elo on LiveCodeBench Pro — fit for autonomous agents and multi-step engineering tasks.
View Documentation →
1M-token multimodal understanding
Accepts text, images, video, audio, and PDF as input with a 1M-token context and 64K max output, reasoning across mixed media and long documents in a single request.
View Documentation →
Tool use for real agents
Supports function calling, structured output, search grounding and integration, and code execution, so agents can call tools, ground answers in search, and run code end to end.
View Documentation →
How to deploy the Gemini 3.1 Pro API on Velokey
Get started with just a few steps.
Sign up and get an API Key
Sign in to the Velokey console to generate an API Key that authenticates every request sent to Gemini 3.1 Pro.
Configure request parameters
Set model to gemini-3-1-pro and submit messages. Attach text, images, video, audio, or PDF, and enable function calling, structured output, search grounding, and code execution.
Integrate and start calling
Send requests to Velokey's unified endpoint to power agents, assistants, and automation, with usage managed in one console.
Real-world use cases for Gemini 3.1 Pro
From engineering to research, covering many high-autonomy scenarios.
Agentic applications
With advanced agentic coding and 80.6% on SWE-Bench Verified, fit for autonomous agents that plan, act, and iterate over long tasks.
Advanced coding & refactoring
Strong on standard and agentic coding with 2887 Elo on LiveCodeBench Pro — fit for development, refactoring, and bug fixing.
Long-context document understanding
A 1M-token input context fits entire codebases, long contracts, and dozens of PDFs for retrieval, synthesis, and QA.
Multimodal reasoning
Understands text, images, video, and audio together — fit for analysis over screenshots, diagrams, recordings, and mixed media.
Algorithmic development
Deep, nuanced reasoning with 94.3% on GPQA Diamond — fit for research, algorithm design, and hard analytical work.
Multilingual assistants
Scores 92.6% on multilingual MMMLU — fit for assistants and workflows that span many languages.
Why choose Velokey for Gemini 3.1 Pro
Discount on list price
Call Gemini 3.1 Pro at a lower price on Velokey — pay-as-you-go with no forced subscription, reducing upfront cost.
Unified API interface
One API key accesses Gemini 3.1 Pro and other models — no juggling multiple accounts and keys, simplifying integration.
Complete docs and integration guidance
Endpoint references, parameter details, and multimodal and tool-use examples help you integrate quickly.
Stable and highly available
Automatic failover and stable fallback routes maintain availability when the primary route is down, keeping production reliable.
API Reference
Complete API call examples and parameter descriptions
Endpoint
https://api.velokey.ai/v1beta/models/{model}:generateContentAuthentication
Bearer YOUR_API_KEYRequest Example
curl https://api.velokey.ai/v1beta/models/{model}:generateContent \
-X POST \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-pro-preview",
"messages": [{"role": "user", "content": "Hello!"}],
"temperature": 0.7
}'Response Example
{
"id": "req_abc123",
"model": "gemini-3.1-pro-preview",
"created": 1234567890,
"data": { ... }
}Gemini 3.1 Pro API FAQ
What is Gemini 3.1 Pro best at?
It is Google DeepMind's preview model built for reasoning with unprecedented depth and nuance, advanced standard and agentic coding, long-context document understanding, multimodal reasoning, and algorithmic development.
What inputs and context does it support?
It accepts multimodal input — text, images, video, audio, and PDF — and produces text output, with a 1M-token input context and up to 64K output tokens. Its knowledge cutoff is January 2025.
How does it perform on benchmarks?
It scores 44.4% on Humanity's Last Exam (no tools), 94.3% on GPQA Diamond, 80.6% on SWE-Bench Verified, 2887 Elo on LiveCodeBench Pro, and 92.6% on multilingual MMMLU.
What tool capabilities are available?
Gemini 3.1 Pro supports function calling, structured output, search grounding and integration, and code execution, so you can build agents that call tools, search, and run code.
How is it billed on Velokey?
This page's pricing area shows the current Velokey price, billed by input and output tokens with a discount on list price. One API key accesses Gemini 3.1 Pro through the unified endpoint.
Start building with Gemini 3.1 Pro Preview today
Use one API key to access low-cost, stable AI models through Velokey.