Models / Uncensored / Google (community tune)
Gemma 4 31B MeroMero v2 API pricing
$0.35 in, $1.575 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | Google (community tune) list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $0.35 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $1.575 | — |
Gemma 4 31B MeroMero v2 specs
- Context window
- 262,144 tokens
- Max output
- 32,768 tokens
- Input
- text and image
Gemma 4 31B MeroMero v2: zerofata’s narrative roleplay tune · more varied swipes than MeroMero v1 and stock Gemma 4
Gemma 4 31B MeroMero v2 is zerofata's fine-tune of Google's Gemma 4 31B it for creative tasks, narrative roleplay above all (its card, created 2026-07-31). It was made in stages: a diversity SFT on about 4,000 short stories, SLERP-merged back into the instruct model at half weight, a creative GRPO run, a roleplay-logic GRPO run with thinking on, then an on-policy roleplay SFT. On the card's own swipe-diversity test it scores 0.72 with thinking off, against 0.57 for MeroMero v1 and 0.43 for stock Gemma 4, with IFEval, GSM8K and MMLU-Pro about level with stock. It is served as gemma-4-31b-meromero-v2 at $0.35 input and $1.575 output per million tokens, one of 146 builds in the uncensored LLM API, on the same key as every other model. Added 2026-10-20.
| Gemma 4 31B MeroMero v2 | |
|---|---|
| Base model | Gemma 4 31B it |
| Made by | zerofata |
| Method | SFT, merge, two GRPO stages, on-policy SFT |
| License on the card | apache-2.0 |
| Context window here | 262,144 tokens |
| Downloads, 30 days to 2026-10-20 | 1,116 |
| Card | zerofata/G4-MeroMero-v2-31B |
From the Hugging Face card and its API record, read 2026-10-20.
The card recommends temperature 0.8 to 1.0 and min_p 0.05, and supports both thinking and non-thinking.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"gemma-4-31b-meromero-v2","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Gemma 4 31B MeroMero v2 next to the other uncensored models · per million tokens, live
A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.
Worked for Gemma 4 31B MeroMero v2: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.35 input and $1.575 output per million tokens, that is $0.70 + $0.7875 = $1.49, paid from prepaid credit with no subscription.
Gemma 4 31B MeroMero v2 API · base URL and key
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="gemma-4-31b-meromero-v2",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'gemma-4-31b-meromero-v2',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"gemma-4-31b-meromero-v2","messages":[{"role":"user","content":"Hello"}]}'What would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.
More from Google (community tune)
Gemma 4 31B MeroMero v2 questions
- What is Gemma 4 31B MeroMero v2?
- Gemma 4 31B MeroMero v2 is a model from Google (community tune), with a 262,144-token context window, taking text and image input. Through UplinkSwitch it answers the OpenAI SDK on one key as gemma-4-31b-meromero-v2.
- How much does the Gemma 4 31B MeroMero v2 API cost?
- $0.35 per million input tokens and $1.575 per million output tokens.
- Is Gemma 4 31B MeroMero v2 free?
- It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0011.
- What is the Gemma 4 31B MeroMero v2 context window?
- Gemma 4 31B MeroMero v2 has a 262,144-token context window, with up to 32,768 output tokens per request. It takes text and image input.
- What is the Gemma 4 31B MeroMero v2 model id?
- gemma-4-31b-meromero-v2. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Gemma 4 31B MeroMero v2 API key?
- Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls Gemma 4 31B MeroMero v2 and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is it the real Gemma 4 31B MeroMero v2?
- Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. Gemma 4 31B MeroMero v2's latest result: Same fingerprint since Oct 20.
- Is there a Gemma 4 31B MeroMero v2 API?
- Yes: gemma-4-31b-meromero-v2 on the OpenAI format at https://api.uplinkswitch.com/v1, $0.35 input and $1.575 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.
- What is Gemma 4 31B MeroMero v2 based on?
- Google’s Gemma 4 31B it, trained by zerofata through SFT, a merge, two GRPO stages and an on-policy roleplay SFT, per its card. It is the more creative successor to MeroMero 31B.
- What license does Gemma 4 31B MeroMero v2 have?
- The card lists Apache-2.0.
- What does Gemma 4 31B MeroMero v2 cost per 100 messages?
- $0.1488 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.35 input and $1.575 output per million tokens, from prepaid credit with no subscription.
- What settings does MeroMero v2 use?
- Its card recommends temperature 0.8 to 1.0 and min_p 0.05, with the Gemma 4 instruct template in Think or NoThink form; it suggests actions in plain text, dialogue in quotes and thoughts in asterisks.
- Gemma 4 31B MeroMero v2 or Gemma 4 26B-A4B MeroMero?
- MeroMero v2 is the 31B dense Gemma 4 tune; the 26B-A4B MeroMero is the Gemma 4 mixture-of-experts build. Gemma 4 31B MeroMero v2 is $0.35 / $1.575 per million tokens in / out, $1.49 for 1,000 chat turns; Gemma 4 26B-A4B MeroMero is $0.42 / $1.33 per million tokens in / out, $1.51 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.