gemini-3-flash-preview-thinking
Gemini 3 · Per Token
gemini-3-flash-preview-thinkingAvailable⚡Cache 90% offChatReasoningVisionTool UsePrompt CacheJSON ModeFastPreviewContext Window: 1049KMax Output Tokens: 66K
Pricing
| Official Price | LemonData Price | |
|---|---|---|
| Input | $0.50 | $0.35 |
| Output | $3.00 | $2.10 |
| Cache Read | $0.05 | $0.05 |
Parameters
Context Window
1.0M tokens
Max Output Tokens
66K tokens
Best For
Chat
Conversational AI, customer support, and Q&A
Reasoning
Complex reasoning tasks, analytical work, and research
Vision
Image understanding, document analysis, and visual reasoning
Cost Calculator
1M
0.5M
Estimated Monthly Cost$1.40
API Code Example
POST/v1beta/models/gemini-3-flash-preview-thinking:generateContent
curl "https://api.lemondata.cc/v1beta/models/gemini-3-flash-preview-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-3-flash-preview-thinking cost?
On LemonData, gemini-3-flash-preview-thinking costs $0.3500 per 1M input tokens and $2.1000 per 1M output tokens, which is up to 30% off the official pricing.
What is gemini-3-flash-preview-thinking best for?
gemini-3-flash-preview-thinking excels at Chat, Reasoning, Vision. Access it through LemonData's unified API with a single API key.
How to use gemini-3-flash-preview-thinking API?
Get your API key from LemonData, set the base URL to api.lemondata.cc/v1, and use any OpenAI-compatible SDK. See the code examples above.
