Gemini 3 Flash

Google

Get an API key

Google's Gemini 3 generation Flash model. Faster and more capable than Gemini 2.5 Flash.

Streaming JSON mode Tool calling Vision Multilingual

Model highlights

Gemini 3 generation
Ultra-fast responses
Improved over 2.5 Flash
Cost-efficient
Multi-modal support

Modalities: IntextimageOuttext
Input / output: $0.50 / $3.00USD per 1M tokens
Context: 1M
Providers: 2 live
Released: Dec 17, 2025
Knowledge cutoff: January 2025

Playground

Preparing playground

Providers


	primary	4.4s	100%
	fallback	—	—

Performance

Response latency estimates

Time to first token

Generation speed · tok/s

Request success

Text-model timing and speed, plus API request success. Daily latency percentiles are estimates. Your request logs

API

POST/api/v1/chat/completionsOpenAI-compatible

gemini-3-flash

curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-flash",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'

messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choiceresponse_formatimage_url content parts

Pricing

Input: $0.50/M tokens
Cached input: $0.05/M tokens
Output: $3.00/M tokens

Published USD rates. Actual cost depends on input, output, cache usage and request options.