Gemma 3 12B

DeepInfra

Google's compact multimodal Gemma 3 model for inexpensive vision and tool workloads.

Modalities
IntextimageOuttext
Input / output
$0.05 / $0.15USD per 1M tokens
Context
131K
Providers
Live

Playground

Preparing playground

Providers

primary

API

POST/api/v1/chat/completionsOpenAI-compatible
gemma-3-12b
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-3-12b",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choiceimage_url content parts

Pricing

Input
$0.05/M tokens
Cached input
$0.005/M tokens
Output
$0.15/M tokens

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