---
id: "google/gemma-3-12b-it"
also: ["google/gemma-3-12b-it", "hf/google/gemma-3-12b-it"]
cheapest_list_usd_per_m: "0.04 in, 0.12 out, at deepinfra/bf16/flex on openrouter"
cheapest_effective_usd_per_m: "0.0394 in, 0.0994 out, at deepinfra/bf16/flex on openrouter"
context: 131072
max_output: 16384
input: ["text", "image"]
output: ["text"]
released: "2025-03-13"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 6
gateways: "openrouter (4), hf (2)"
no_training: 4
trains: 0
retains_prompts: 0
coding: 5.8000
agentic: 0.1000
---
# Google: Gemma 3 12B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...