Models / Uncensored / huihui-ai
Llama 3.3 70B Abliterated API pricing
$2.10 in, $2.10 out per million tokens.
Price · per million tokens, USD
| Tokens | huihui-ai list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $2.10 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $2.10 | — |
Llama 3.3 70B Abliterated specs
- Context window
- 32,768 tokens
- Input
- text
Llama 3.3 70B Abliterated: uncensored Llama by API · huihui-ai’s abliteration, per token, no 70B download
Llama 3.3 70B Abliterated is Meta's Llama 3.3 70B Instruct with the direction that makes it refuse removed from its weights by huihui-ai (its card, with 21,795 Hugging Face downloads in the 30 days to 2026-10-20). Abliteration retrains nothing, so the model keeps what Llama 3.3 knows. You call it instead of downloading 70B weights and running them on your own GPUs. It is served as llama-3.3-70b-abliterated at $2.10 input and $2.10 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.
| Llama 3.3 70B Abliterated | |
|---|---|
| Base model | Llama 3.3 70B Instruct |
| Made by | huihui-ai |
| Method | Abliteration, no retraining |
| License on the card | llama3.3 |
| Context window here | 32,768 tokens |
| Downloads, 30 days to 2026-10-20 | 21,795 |
| Card | huihui-ai/Llama-3.3-70B-Instruct-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":"llama-3.3-70b-abliterated","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Llama 3.3 70B 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 Llama 3.3 70B Abliterated: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $2.10 input and $2.10 output per million tokens, that is $4.20 + $1.05 = $5.25, paid from prepaid credit with no subscription.
Llama 3.3 70B 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="llama-3.3-70b-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: 'llama-3.3-70b-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":"llama-3.3-70b-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.
More from huihui-ai
Llama 3.3 70B Abliterated questions
- What is Llama 3.3 70B Abliterated?
- Llama 3.3 70B Abliterated is a model from huihui-ai, with a 32,768-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as llama-3.3-70b-abliterated.
- How much does the Llama 3.3 70B Abliterated API cost?
- $2.10 per million input tokens and $2.10 per million output tokens.
- Is Llama 3.3 70B 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 $0.0032.
- What is the Llama 3.3 70B Abliterated context window?
- Llama 3.3 70B Abliterated has a 32,768-token context window. It takes text input.
- What is the Llama 3.3 70B Abliterated model id?
- llama-3.3-70b-abliterated. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Llama 3.3 70B 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 Llama 3.3 70B 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 Llama 3.3 70B Abliterated API?
- Yes: llama-3.3-70b-abliterated on the OpenAI format at https://api.uplinkswitch.com/v1, $2.10 input and $2.10 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 Llama 3.3 70B Abliterated based on?
- Meta’s Llama 3.3 70B Instruct, with the refusal direction removed by huihui-ai’s abliteration (no retraining), per its card.
- What license does Llama 3.3 70B Abliterated have?
- The card lists the Llama 3.3 license, inherited from Meta’s Llama 3.3 70B Instruct.
- What does Llama 3.3 70B Abliterated cost per 100 messages?
- $0.525 for 100 chat turns of 2,000 input and 500 output tokens each, at $2.10 input and $2.10 output per million tokens, from prepaid credit with no subscription.
- Can I run Llama 3.3 70B Abliterated without a GPU?
- Yes, through the API: send llama-3.3-70b-abliterated to https://api.uplinkswitch.com/v1 with your key. There is no 70B file to download and no GPU to rent; 100 chat turns cost $0.525 at $2.10 input and $2.10 output per million tokens.
- What does abliterated mean for Llama 3.3?
- The direction in the model’s activations that separates refused prompts from answered ones is found and projected out of the weights. Nothing is retrained, so Llama 3.3 70B keeps what it knows and stops declining the prompts it used to refuse.