G

Google: Gemini 2.0 Flash Thinking Experimental

Google
Vision Tools Streaming
1M
Context
$0.1000
Input /1M
$0.4000
Output /1M
8K
Max Output
Run API Call Open in Chat

Google: Gemini 2.0 Flash Thinking Experimental

Model Overview

Property Value
Model ID google/gemini-2.0-flash-thinking-exp
Name Gemini 2.0 Flash Thinking Experimental
Provider Google
Released December 2024

Description

An experimental version of Gemini 2.0 Flash with enhanced reasoning capabilities. This model features a "thinking" mode that allows it to work through complex problems step-by-step before providing final answers.

Specifications

Spec Value
Context Window 1,000,000 tokens
Max Completion 8,192 tokens
Modalities Text, Image, Audio, Video

Pricing

Type Price
Input $0.10 per 1M tokens
Output $0.40 per 1M tokens

Capabilities

  • Vision: Yes
  • Tool Use: Yes
  • JSON Mode: Yes
  • Streaming: Yes
  • Function Calling: Yes
  • Reasoning/Thinking: Yes

Use Cases

Complex problem-solving, multi-step reasoning, mathematical proofs, logical analysis, and tasks requiring detailed thought processes.

Integration with LangMart

Gateway Support: Type 2 (Cloud), Type 3 (Self-hosted)

API Usage:

curl -X POST https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.0-flash-thinking-exp",
    "messages": [{"role": "user", "content": "Solve this step by step"}],
    "max_tokens": 8192
  }'
  • google/gemini-2.0-flash - Standard Flash model
  • google/gemini-2.0-flash-thinking-exp-1219 - December 19 version
  • google/gemini-2.0-flash-thinking-exp-01-21 - January 21 version

Notes

Experimental model with thinking capabilities. May show reasoning steps in output. Latency may be higher for complex queries.

Last Updated: December 28, 2025