gemini-2.5-pro-thinking

Gemini 2.5 · Per Token

gemini-2.5-pro-thinkingAvailableCache 90% off
ChatVisionReasoningTool UsePrompt CacheJSON ModeFastPremiumContext Window: 1000KMax Output Tokens: 66K

Pricing

Official PriceLemonData Price
Input$1.25$0.875
Output$18.00$12.60
Cache Read$0.125$0.125

Parameters

Context Window
1.0M tokens
Max Output Tokens
66K tokens

Best For

Chat

Conversational AI, customer support, and Q&A

Vision

Image understanding, document analysis, and visual reasoning

Reasoning

Complex reasoning tasks, analytical work, and research

Cost Calculator

1M
0.5M
Estimated Monthly Cost$7.17

API Code Example

POST/v1beta/models/gemini-2.5-pro-thinking:generateContent
API Format:
curl "https://api.lemondata.cc/v1beta/models/gemini-2.5-pro-thinking:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: sk-xxx" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Hello!"}]}
    ]
  }'

FAQ

How much does gemini-2.5-pro-thinking cost?

On LemonData, gemini-2.5-pro-thinking costs $0.8750 per 1M input tokens and $12.6000 per 1M output tokens, which is up to 30% off the official pricing.

What is gemini-2.5-pro-thinking best for?

gemini-2.5-pro-thinking excels at Chat, Vision, Reasoning. Access it through LemonData's unified API with a single API key.

How to use gemini-2.5-pro-thinking API?

Get your API key from LemonData, then call https://api.lemondata.cc/v1beta/models/gemini-2.5-pro-thinking:generateContent using any compatible SDK. See the code examples above for detailed integration.

Related Models