Providers

Google

Verified

Google DeepMind's Gemini family — natively multimodal frontier models served on Google's own AI infrastructure.

Start building View requests Official status

Models on Google

Open in catalog

16 of 16

Gemini 2.5 FlashChatgemini-2.5-flashReleased Jun 17, 20251M contextRouteprimary$0.30 / $2.50per M input / output

Gemini 2.5 ProChatgemini-2.5-proReleased Jun 17, 20251M contextRouteprimary$1.25 / $10.00per M input / output

Gemini 3 FlashChatgemini-3-flashReleased Dec 17, 20251M contextRouteprimary$0.50 / $3.00per M input / output

Gemini 3 ProChatgemini-3-pro1M contextRouteprimary$2.00 / $12.00per M input / output

Gemini 3.1 ProChatgemini-3.1-proReleased Feb 19, 20261M contextRouteprimary$2.00 / $12.00per M input / output

Gemini 3.5 FlashChatgemini-3.5-flashReleased May 19, 20261M contextRouteprimary$1.50 / $9.00per M input / output

Gemini 3.5 Flash-LiteChatgemini-3.5-flash-lite1M contextRouteprimary$0.30 / $2.50per M input / output

Gemini 3.6 FlashChatgemini-3.6-flashReleased Jul 21, 20261M contextRouteprimary$1.50 / $7.50per M input / output

Gemini 3.7 FlashChatgemini-3.7-flash1M contextRouteprimary$0.75 / $3.75per M input / output

Gemini 3.8 FlashChatgemini-3.8-flash1M contextRouteprimary$0.75 / $3.75per M input / output

Gemini Omni FlashVideogemini-omni-flashRouteprimary$1.05/video

Nano BananaImagenano-bananaRouteprimary$0.039/image

Nano Banana 2Imagenano-banana-2Routeprimary$0.067/image

Nano Banana ProImagenano-banana-proRouteprimary$0.134/image

Veo 3.1Videoveo-3.1Routeprimary$3.2/video

Veo 3.1 FastVideoveo-3.1-fastRouteprimary$1.2/video

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.

Direct routingCall Google explicitly

google· routing

# pin every request to Google
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "routing": { "providers": { "only": ["google"] } }
  }'