OPHIRISOpen app

Meta · Open weights

Llama 3.3 70B Instruct abliterated

Added Aug 8, 2025Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

An abliterated (removed restrictions and censorship) version of Llama 3.3 70b.

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.70
Output
$0.70
Cache read
$0.35

Reference prices as published by the model provider. API example

Specifications

Context window
32.8K
Max output
—

Side by side

Llama 3.3 70B Instruct abliterated compared

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

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Llama 3.3 70B Instruct abliteratedMetaThis modelMiMo V2.6 Flash Uncensored ThinkingxiaomiRemove
ProviderMetaxiaomi
Discovery tierOpen weightsOpen weights
AddedAug 8, 2025Sep 26, 2026
Limits
Context window32.77K1.05MBest
Max output—65.54K
Pricing, USD per 1M tokens
Input$0.70$0.50Best
Output$0.70Best$1.50
Cache read$0.35$0.20Best
Performance
Throughput19.7 tok/s123.5 tok/sBest
Time to first token2.0 s1.6 sBest
Request success (24h)73.5%91.8%Best
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Reasoning effort—max

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Ophiris catalog.

  • Llama 3.3 70B Instruct abliterated
  • MiMo V2.6 Flash Uncensored Thinking
LeaderboardLlama 3.3 70B Instruct abliteratedMiMo V2.6 Flash Uncensored Thinking
Uncensored#1 · 37.5%Not in top 20

Ranks among Ophiris catalog models on Use cases leaderboards. Only top-20 placements are listed.

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.

Throughput
19.7 tok/s
Faster than 15% of 52 models
Time to first token
2.0 s
Quicker than 86% of 52 models
Prompt cache hits
0.0%
About $0.70 per 1M input tokens with caching
Request success (24h)
73.5%

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Developers

Use it through the API

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

Read the quickstart
request.sh
curl https://www.ophiris.xyz/api/v1/chat/completions \  -H "Authorization: Bearer $OPHIRIS_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "huihui-ai/Llama-3.3-70B-Instruct-abliterated",    "messages": [{ "role": "user", "content": "Explain this stack trace." }]  }'
client.py
import osfrom openai import OpenAI client = OpenAI(base_url="https://www.ophiris.xyz/api/v1", api_key=os.environ["OPHIRIS_API_KEY"])reply = client.chat.completions.create(    model="huihui-ai/Llama-3.3-70B-Instruct-abliterated",    messages=[{"role": "user", "content": "Explain this stack trace."}],)print(reply.choices[0].message.content)

Meta

Other Meta models, starting with the same family.