Meta · Open weights

Llama 3 70B abliterated

Added Jul 26, 2025Open weights

Use in the app

An abliterated (removed restrictions and censorship) version of Llama 3.1 70b.

Input: Text
Output: Text
Discovery tier: Open weights

Pricing

USD per 1M tokens

Input: $0.70
Output: $0.70

Reference prices as published by the model provider. API example

Specifications

Context window: 8.2K
Max output: —
Average output (7 days): 168 tokens; Longer than 17% of 465 models

Side by side

Llama 3 70B abliterated compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Limits
	Llama 3 70B abliteratedMetaThis model	Qwen 2.5 32B AbliteratedQwenRemove
Provider	Meta	Qwen
Discovery tier	Open weights	Open weights
Added	Jul 26, 2025	Jan 6, 2025
Context window	8.19K	32.77KBest
Max output	—	8.19K
Average output	168 tokens	806 tokens
Pricing, USD per 1M tokens
Input	$0.70	$0.70
Output	$0.70	$0.70
Performance
Throughput	—	9.2 tok/s
Time to first token	—	4.9 s
Request success (24h)	17.9%	60.3%Best
Capabilities
Reasoning effort	—	—

Public evaluations

Benchmarks

There are no public benchmark results for these models yet.

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Request success (24h): 17.9%

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart

curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)