Models / Uncensored / mlabonne
NeuralDaredevil 8B Abliterated API pricing
$1.32 in, $1.32 out per million tokens.
Price · per million tokens, USD
| Tokens | mlabonne list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $1.32 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $1.32 | — |
NeuralDaredevil 8B Abliterated specs
- Context window
- 8,192 tokens
- Input
- text
NeuralDaredevil 8B Abliterated: abliterated, then repaired · Maxime Labonne’s DPO fine-tune of an abliterated 8B
NeuralDaredevil 8B Abliterated is Maxime Labonne's DPO fine-tune of his Daredevil 8B Abliterated, trained for one epoch on orpo-dpo-mix-40k (its card; 15,217 downloads in the 30 days to 2026-10-20). The card says the DPO pass recovers the performance abliteration costs, and that it scored better than the Instruct model in his tests. Labonne also wrote the abliteration explainer on Hugging Face. It is served as neuraldaredevil-8b-abliterated at $1.32 input and $1.32 output per million tokens, one of 49 builds in the uncensored LLM API, on the same key as every other model. Added 2026-10-20.
| NeuralDaredevil 8B Abliterated | |
|---|---|
| Base model | Daredevil 8B Abliterated (Llama 3 8B) |
| Made by | Maxime Labonne (mlabonne) |
| Method | Abliteration, then DPO |
| License on the card | llama3 |
| Context window here | 8,192 tokens |
| Downloads, 30 days to 2026-10-20 | 15,217 |
| Card | mlabonne/NeuralDaredevil-8B-abliterated |
From the Hugging Face card and its API record, read 2026-10-20.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"neuraldaredevil-8b-abliterated","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'NeuralDaredevil 8B Abliterated 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 NeuralDaredevil 8B Abliterated: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $1.32 input and $1.32 output per million tokens, that is $2.64 + $0.66 = $3.30, paid from prepaid credit with no subscription.
NeuralDaredevil 8B Abliterated 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="neuraldaredevil-8b-abliterated",
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: 'neuraldaredevil-8b-abliterated',
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":"neuraldaredevil-8b-abliterated","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.
NeuralDaredevil 8B Abliterated questions
- What is NeuralDaredevil 8B Abliterated?
- NeuralDaredevil 8B Abliterated is a model from mlabonne, with a 8,192-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as neuraldaredevil-8b-abliterated.
- How much does the NeuralDaredevil 8B Abliterated API cost?
- $1.32 per million input tokens and $1.32 per million output tokens.
- Is NeuralDaredevil 8B Abliterated 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 $0.002.
- What is the NeuralDaredevil 8B Abliterated context window?
- NeuralDaredevil 8B Abliterated has a 8,192-token context window. It takes text input.
- What is the NeuralDaredevil 8B Abliterated model id?
- neuraldaredevil-8b-abliterated. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a NeuralDaredevil 8B Abliterated 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 NeuralDaredevil 8B Abliterated and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is there a NeuralDaredevil 8B Abliterated API?
- Yes: neuraldaredevil-8b-abliterated on the OpenAI format at https://api.uplinkswitch.com/v1, $1.32 input and $1.32 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 NeuralDaredevil 8B Abliterated based on?
- mlabonne’s Daredevil-8B-abliterated (a Llama 3 8B merge with the refusal direction removed), then one epoch of DPO on orpo-dpo-mix-40k, per its card.
- What license does NeuralDaredevil 8B Abliterated have?
- The card’s license tag is llama3.
- What does NeuralDaredevil 8B Abliterated cost per 100 messages?
- $0.33 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.32 input and $1.32 output per million tokens, from prepaid credit with no subscription.
- Why fine-tune a model after abliterating it?
- Removing the refusal direction can cost some quality. NeuralDaredevil’s card says one epoch of DPO on orpo-dpo-mix-40k recovered that loss, so it stays uncensored and scores better than the Instruct model in its author’s tests.