Gemini 3 Pro Preview API

Gemini 3 Pro is Google’s latest iteration in the Gemini series.
Output

How to use Gemini 3 Pro Preview API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to .

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Gemini 3 Pro Preview API Pricing

TypePrice
Input
Output

Gemini 3 Pro Preview Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Intelligence
28
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Math
95.7
Composite score across standardised mathematics evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Gemini 3 Pro Preview vs other models

ModelInputOutputContextBest for
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Yes, Gemini 3 Pro Preview can stream responses as they are generated.

Yes, Gemini 3 Pro Preview supports both function calling and structured outputs.

Gemini 3 Pro Preview was built by Google.

It is available at the v1/chat/completions endpoint.

Start building with Gemini 3 Pro Preview

Get API Key
1000+ models, one API.