Models / Llama

4 Llama builds: 2 abliterated, 1 uncensored, 1 roleplay.

Which Llama build to pick

Largest context: 65,536 tokens, Hermes 3 Llama 3.1 70B
Lowest output price: $2.04 per million tokens, Hermes 3 Llama 3.1 70B
Abliterated: Llama 3 70B Abliterated v3.5, $3.50 per million output tokens
Roleplay: Aion RP Llama 3.1 8B, $8.00 per million output tokens
Prices as of: 2026-10-24

Uncensored models and their prices per million tokens
					Wire formats
Aion RP Llama 3.1 8Baion-rp-llama-3.1-8b	Roleplay	$4.00	$8.00	33K	openai
Hermes 3 Llama 3.1 70Bhermes-3-llama-3.1-70b	Uncensored	$2.04	$2.04	66K	openai
Llama 3 70B Abliterated v3.5llama-3-70b-abliterated	Abliterated	$3.50	$3.50	8K	openai
Llama 3.3 70B Abliteratedllama-3.3-70b-abliterated	Abliterated	$3.50	$3.50	33K	openai

Llama abliterated vs uncensored and roleplay builds

Abliterated: 2 builds, output from $3.50 per million tokens, context up to 32,768 tokens
Uncensored: 1 build, output from $2.04 per million tokens, context up to 65,536 tokens
Roleplay: 1 build, output from $8.00 per million tokens, context up to 32,768 tokens

Llama questions

Yes. UncensoredLLM lists 2 abliterated Llama builds: Llama 3 70B Abliterated v3.5 and Llama 3.3 70B Abliterated.

Hermes 3 Llama 3.1 70B, with a 65,536-token context window.

Other families: DeepSeek abliterated models · Qwen abliterated models · Gemma abliterated models · GLM abliterated models