Gemini 2.0 Flash Thinking Experimental API

Gemini 2.0 Flash Thinking Experimental excels in complex reasoning tasks with advanced features like multimodal input support and code execution
Output

How to use Gemini 2.0 Flash Thinking Experimental 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 2.0 Flash Thinking Experimental API Pricing

TypePrice
Input
Output

Gemini 2.0 Flash Thinking Experimental Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Intelligence
9.4
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
24.1
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Gemini 2.0 Flash Thinking Experimental 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 2.0 Flash Thinking Experimental can stream responses as they are generated.

Yes, Gemini 2.0 Flash Thinking Experimental supports both function calling and structured outputs.

Gemini 2.0 Flash Thinking Experimental was built by Google.

Yes, it includes reasoning as one of its capabilities.

Start building with Gemini 2.0 Flash Thinking Experimental

Get API Key
1000+ models, one API.