Run Gemma 4 12B Starry Ocean without a GPU.
Roleplay by Google (community tune), on Unrestrictable as gemma-4-12b-starry-ocean.
Gemma 4 12B Starry Ocean is a roleplay model of Gemma 4 12B. It costs $0.175 per million input tokens and $0.875 per million output tokens, prepaid, with a 131,072-token context window. Call it at https://api.unrestrictable.ai/v1/chat/completions with model "gemma-4-12b-starry-ocean" and an Unrestrictable key, from any OpenAI SDK or client that takes a base URL.
Price per million tokens
- Input
- $0.175
- Cached input
- $0.0875
- Output
- $0.875
- Success rate
- 98.1% of 104 requests, last 24 hours
- Daily check
- Steady since Oct 23
- As of
- 2026-11-16
First request
curl https://api.unrestrictable.ai/v1/chat/completions \ -H "Authorization: Bearer sk-unr-live-…" \ -H "Content-Type: application/json" \ -d '{"model": "gemma-4-12b-starry-ocean", "messages": [{"role": "user", "content": "Hello"}]}'Gemma 4 12B Starry Ocean settings for SillyTavern and Janitor AI
- SillyTavern API
- Chat Completion
- Source
- Custom (OpenAI-compatible)
- Custom endpoint
- https://api.unrestrictable.ai/v1
- Model
- gemma-4-12b-starry-ocean
- Context Size
- 131,072 tokens
- Janitor AI proxy URL
- https://api.unrestrictable.ai/v1/chat/completions
- Key prefix
- sk-unr-
Gemma 4 12B Starry Ocean specs
- Kind
- Roleplay
- Developer
- Google (community tune)
- Base model
- Gemma 4 12B
- Context window
- 131,072 tokens
- Input
- text and image
- Wire formats
- openai
Get a key
- Create a key in the console. Credit is prepaid from $10, with no subscription.
- Set OPENAI_BASE_URL to https://api.unrestrictable.ai/v1 and send your sk-unr- key as the bearer token.
- Send gemma-4-12b-starry-ocean as the model. The same key calls every model on Unrestrictable.
What Gemma 4 12B Starry Ocean is
- Base model
- Made by
- Vortex5
- Method
- Custom merge of two Gemma 4 12B tunes
- License on the card
- apache-2.0
- Downloads, 30 days to 2026-10-20
- 166
- Context window here
- 131,072 tokens
- Input
- text and image
From the SDK
from openai import OpenAI client = OpenAI(base_url="https://api.unrestrictable.ai/v1", api_key="sk-unr-live-…") completion = client.chat.completions.create( model="gemma-4-12b-starry-ocean", messages=[{"role": "user", "content": "Hello"}],)print(completion.choices[0].message.content)import OpenAI from 'openai'; const client = new OpenAI({ baseURL: 'https://api.unrestrictable.ai/v1', apiKey: 'sk-unr-live-…' }); const completion = await client.chat.completions.create({ model: 'gemma-4-12b-starry-ocean', messages: [{ role: 'user', content: 'Hello' }],});console.log(completion.choices[0].message.content);What Gemma 4 12B Starry Ocean is built to write
Gemma 4 12B Starry Ocean is a fiction fine-tune: trained on long-form stories and character dialogue, it holds a character's voice, follows a scenario and writes at length without the stock refusal layer.
Every request is routed to the build’s live route and settled to the token at the prices above. The daily real-model check sends a fixed prompt to every model and records whether the answer still matches; this model’s verdict today is “Steady since Oct 23”.
Use it from the OpenAI SDK, from SillyTavern or Janitor, or from a coding agent. Keys and top-ups live in the console.
More from Google (community tune)
What Gemma 4 12B Starry Ocean costs, worked
A chat turn of 2,000 input and 500 output tokens at $0.175 input and $0.875 output per million tokens is $0.0008; 1,000 turns are $0.79. A long chat session of 100 replies of 300 tokens costs $0.0963 at 4,000 tokens of context and $0.3063 at 16,000: every message resends the context, so size it to what the chat needs. All from prepaid credit, no subscription.
| Roleplay builds | Context | In / out per 1M | 1,000 chat turns |
|---|---|---|---|
| Manta Flash 1.0 | 16K | $0.07 / $0.56 | $0.42 |
| Manta Mini 1.0 | 8K | $0.07 / $0.56 | $0.42 |
| Gemma 4 12B Starry Ocean | 131K | $0.175 / $0.875 | $0.79 |
| Gemma 4 12B StationKeeper | 131K | $0.175 / $0.875 | $0.79 |
| Magidonia 24B v4.3 | 33K | $0.3535 / $0.4235 | $0.92 |
| MythoMax L2 13B | 4K | $0.404 / $0.404 | $1.01 |
| Cydonia 24B v2 | 33K | $0.4012 / $0.4828 | $1.04 |
| Gemma 4 31B Split-Untied | 262K | $0.35 / $1.05 | $1.23 |
| Cydonia 24B v4.3 | 131K | $0.484 / $0.60 | $1.27 |
| Manta Pro 1.0 | 66K | $0.21 / $1.75 | $1.30 |
| Artemis v1.1 | 262K | $0.35 / $1.575 | $1.49 |
| Gemma 4 31B Gembrain | 262K | $0.35 / $1.575 | $1.49 |
| Gemma 4 31B Isometry | 262K | $0.35 / $1.575 | $1.49 |
| Gemma 4 31B Scarlet | 262K | $0.35 / $1.575 | $1.49 |
| Gemma 4 31B Fabled | 262K | $0.35 / $1.575 | $1.49 |
| Gemma 4 31B Gemsicle | 262K | $0.35 / $1.575 | $1.49 |
Gemma 4 12B Starry Ocean in SillyTavern and Janitor AI: what to set
The three fields are the base URL, the key and the model id, as in the settings above. What differs by build is the reply length, the reasoning switch and the context size, and those decide both whether a reply arrives whole and what each message costs.
- Context Size up to 131,072 tokens, the window the catalog lists for gemma-4-12b-starry-ocean. Every message resends the context, so set it to what the chat needs rather than the maximum.
- A fiction tune answers at once, with no reasoning step: a Max Response Length of 300 to 600 tokens fits a chat reply.
A request that fails before the model answers is not billed. A refusal written as ordinary text is billed like any answer, which is the reason to send this build rather than a stock model with a preamble: the build does not write one.
What Gemma 4 12B Starry Ocean costs by client
| Session | What is sent | At the live price |
|---|---|---|
| SillyTavern or Janitor AI, one evening | 100 replies of 300 tokens on 4,000 tokens of context | $0.0963 |
| The same evening on a long chat | 100 replies of 300 tokens on 16,000 tokens of context | $0.3063 |
| A month of short turns | 1,000 turns of 2,000 input and 500 output tokens | $0.7875 |
| One long document, summarised once | 100,000 input and 1,000 output tokens in one request | $0.0184 |
Gemma 4 12B Starry Ocean questions
Gemma 4 12B Starry Ocean is a roleplay build of Gemma 4 12B from Google (community tune), with a 131,072-token context window, taking text and image input. On Unrestrictable it answers as gemma-4-12b-starry-ocean.
No. Credit is prepaid from $10 and billed per token: input $0.175 and output $0.875 per million tokens, cached input $0.0875.
About $0.0006 for 1,000 tokens in and 500 tokens out, at $0.175 in and $0.875 out per million tokens.
Up to 131,072 tokens, the context window the catalog lists for Gemma 4 12B Starry Ocean.
Yes. Send gemma-4-12b-starry-ocean as the model through the OpenAI SDK, or any client that takes a custom OpenAI base URL, with base URL https://api.unrestrictable.ai/v1.
In SillyTavern, set API to Chat Completion, Source to Custom (OpenAI-compatible) and the custom endpoint to https://api.unrestrictable.ai/v1, paste your key, then pick gemma-4-12b-starry-ocean from the list it loads. In Janitor AI, choose Proxy, set the URL to https://api.unrestrictable.ai/v1/chat/completions, paste your key and type gemma-4-12b-starry-ocean as the model. See the docs.
Yes. The daily real-model check sends every model the same fixed prompt and records whether the answer still matches. Gemma 4 12B Starry Ocean’s latest result, from Nov 16: steady since Oct 23. See the daily check.
Measured on live traffic over the last 24 hours: 98.1% of 104 requests to Gemma 4 12B Starry Ocean succeeded.
Google’s Gemma 4 12B it, by way of Vortex5’s merge of Semancer-12B and G4-12B-Station-Keeper, per its card.
The card lists Apache-2.0, the license of Gemma 4.
Yes, the weights are on Hugging Face (Vortex5/G4-Starry-Ocean-12B, apache-2.0, read 2026-10-20). Sending gemma-4-12b-starry-ocean to https://api.unrestrictable.ai/v1 needs no download and no GPU: 100 replies cost $0.0963 at the live price.
$0.0788 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.175 input and $0.875 output per million tokens, from prepaid credit with no subscription.
Yes, with the settings above: Chat Completion with a Custom (OpenAI-compatible) source and https://api.unrestrictable.ai/v1 as the endpoint in SillyTavern; the proxy URL https://api.unrestrictable.ai/v1/chat/completions and gemma-4-12b-starry-ocean as the model in Janitor AI. See the SillyTavern guide.