AI model
google/gemma-3-12b-it
Google: Gemma 3 12B is a 131,072-token model served on Composite at $0.0500 per million tokens in and $0.150 per million tokens out.
Try in Playground| Model ID | google/gemma-3-12b-it |
|---|---|
| Provider | DeepInfra |
| Context window | 131,072 tokens |
| Accepts | text, image |
| Returns | text |
| Input price | $0.0500 per million tokens |
| Output price | $0.150 per million tokens |
| Prompt caching | Not offered for this model |
| Moderated | No |
| Cost on a monthly plan | About 0.4 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 2 (base plus 1 routing variant) |
Make a Composite API key and type google/gemma-3-12b-it as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.
The same model behind 1 alternative endpoint. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| cheapThink | google/gemma-3-12b-it:cheapThink |
DeepInfra | $0.0500 per million tokens input · $0.150 per million tokens output |
$0.0500 per million tokens input · $0.150 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 0.4 plan credits, at the provider's own price.
DeepInfra
Gemini models combine large context windows with fast throughput, which keeps response times low even in busy group chats.
With a 131,072-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
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,...
Supplied by DeepInfra, not written by Composite.
Composite Gemini Router · Google: Gemini 3.8 Flash (Drafted) · Google: Gemini 3.7 Flash (Drafted)