Models / Uncensored / inflatebot
Mag Mell R1 12B API pricing
$1.7255 in, $1.7255 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | inflatebot list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $1.7255 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $1.7255 | — |
Mag Mell R1 12B specs
- Context window
- 16,384 tokens
- Max output
- 8,192 tokens
- Input
- text
Mag Mell R1 12B: inflatebot’s “best of Nemo” merge · worldbuilding and prose at 12B, per token
Mag Mell R1 12B is inflatebot's multi-stage merge of Mistral Nemo tunes, meant as a general-purpose “best of Nemo” model for any fictional or creative use (its card, created 2024-09-16, with 3,064 Hugging Face downloads in the 30 days to 2026-10-20). Six models in three pairs were merged with layer-weighted SLERP into specialists (Hero for roleplay, Monk for intelligence, Deity for prose), which were then merged into a ChatML Mistral Nemo base with DARE-TIES. The card claims worldbuilding comparable to Tiefighter and prose with minimal slop. It is served as mag-mell-12b-r1 at $1.7255 input and $1.7255 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.
| Mag Mell R1 12B | |
|---|---|
| Base model | Mistral Nemo Base 2407 (ChatML) |
| Made by | inflatebot |
| Method | Multi-stage merge: SLERP specialists, then DARE-TIES |
| License on the card | none listed (Mistral Nemo: Apache-2.0) |
| Context window here | 16,384 tokens |
| Downloads, 30 days to 2026-10-20 | 3,064 |
| Card | inflatebot/MN-12B-Mag-Mell-R1 |
From the Hugging Face card and its API record, read 2026-10-20.
The card was tested with temperature 1.25 and min_p 0.2, and recommends ChatML without XTC.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"mag-mell-12b-r1","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Mag Mell R1 12B 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 Mag Mell R1 12B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $1.7255 input and $1.7255 output per million tokens, that is $3.451 + $0.8628 = $4.31, paid from prepaid credit with no subscription.
Mag Mell R1 12B 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="mag-mell-12b-r1",
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: 'mag-mell-12b-r1',
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":"mag-mell-12b-r1","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.
Mag Mell R1 12B questions
- What is Mag Mell R1 12B?
- Mag Mell R1 12B is a model from inflatebot, with a 16,384-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as mag-mell-12b-r1.
- How much does the Mag Mell R1 12B API cost?
- $1.7255 per million input tokens and $1.7255 per million output tokens.
- Is Mag Mell R1 12B 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 $0.0026.
- What is the Mag Mell R1 12B context window?
- Mag Mell R1 12B has a 16,384-token context window, with up to 8,192 output tokens per request. It takes text input.
- What is the Mag Mell R1 12B model id?
- mag-mell-12b-r1. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Mag Mell R1 12B 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 Mag Mell R1 12B and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is there a Mag Mell R1 12B API?
- Yes: mag-mell-12b-r1 on the OpenAI format at https://api.uplinkswitch.com/v1, $1.7255 input and $1.7255 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 Mag Mell R1 12B based on?
- IntervitensInc’s Mistral Nemo Base 2407 with ChatML tokens, merged with DARE-TIES with three SLERP specialists built from Chronos Gold, Sunrose, Bophades, Wissenschaft, Gutenberg v4 and Magnum v2.5 KTO, per its card.
- What license does Mag Mell R1 12B have?
- The Mag Mell R1 card lists no license. Mistral Nemo 12B is Apache-2.0.
- What does Mag Mell R1 12B cost per 100 messages?
- $0.4314 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.7255 input and $1.7255 output per million tokens, from prepaid credit with no subscription.
- Is Mag Mell R1 a reasoning model?
- No. Its card says R1 means Revision 1, and that the model predates DeepSeek’s R1.
- Mag Mell R1 12B or NemoMix Unleashed 12B?
- Both are Mistral Nemo 12B merges: Mag Mell is inflatebot’s SLERP-then-DARE-TIES merge, NemoMix Unleashed MarinaraSpaghetti’s DELLA merge. Mag Mell R1 12B is $1.7255 / $1.7255 per million tokens in / out, $4.31 for 1,000 chat turns; NemoMix Unleashed 12B is $1.7255 / $1.7255 per million tokens in / out, $4.31 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.