CLThe Companion Lab
Lab Home › Models & Benchmarks › Euryale 70B & Hermes 4 405B
● Verified Model Telemetry · Oct 2026

Sao10K Llama 3.3 Euryale 70B & Nous Hermes 4 405B (Uncensored Roleplay LLMs)

Built specifically to eliminate the robotic "As an AI, I cannot..." lecture while keeping character voices grounded, Euryale 70B and Hermes 4 405B represent the benchmark for uncensored adult storytelling.

Architecture / Spec
Euryale 70B & Hermes 4 405B
70B Dense Fine-Tune (Euryale v2.3) & 405B Frontier (Hermes 4)
Benchmark / Arena Score
Top 5 Uncensored Creative Writing & Character Continuity
18.6 / 100 (Low Moralizing, Natural Pacing)
Wholesale Cloud API Cost
$0.65 / 1M tokens (Euryale 70B)
Context / Steps: 128,000 Tokens
Commercial App Markup
Included in Flat $13.99–$24.99/mo Literary Companion Plans
Best Value When Bundled in Flat-Rate Companion Apps

Engineering & Roleplay Breakdown

Bounded Plain English Analysis

In our live OpenRouter benchmark, Sao10K’s Euryale 70B and Nous Hermes 4 405B stayed 100% in character during relationship conflict without slipping into therapy-speak or burning 500 tokens on hidden coding logic.

Verified External Authority Sources & Where to Use This Model

OpenRouter · HuggingFace · Civitai · Commercial Apps
Primary Technical SourceExternal Link
OpenRouter: sao10k/l3.3-euryale-70bInspect Source ↗
OpenRouter: nousresearch/hermes-4-405bInspect Source ↗
HuggingFace: Sao10K/L3.3-70B-Euryale-v2.3Inspect Source ↗
Commercial App Running This ClassInternal Bundle Key
Kindroid AI (V8.5 Architecture Class) →Custom Literary 70B+ Cluster
Nomi AI →Proprietary High-EQ Roleplay Stack
Same Prompt, 3 Brains: Live OpenRouter API Roleplay Receipts
Why do companion apps still prefer DeepSeek V3.2 & Euryale 70B over the newer DeepSeek V4.1 Flash? Click a scenario to inspect the actual responses & token receipts.
Prompt Sent:“I just got back from grabbing coffee with my ex. Nothing happened, they just wanted to return my old grey hoodie from three years ago. Why are you looking at me like that?”
DeepSeek V3.2 (671B MoE)Soulmate Gold · 0 CoT Overhead
"Because you're holding a coffee cup that smells like her favorite drink. You never liked vanilla lattes."
22 completion tokens · 0 reasoning_tokens · $0.000053 / reply

Lab Take: In 17 words, V3.2 invents a concrete sensory detail ("vanilla lattes") that catches you in a lie. Zero purple prose, zero wasted tokens—this is why dream-girl (梦女) roleplayers fell in love with V3.2.

DeepSeek V4.1 Flash (2026 Agentic)425 Hidden CoT Tokens · 10.8x Cost
"I set my mug down. Not hard. Just enough. 'I'm not looking at you. I'm looking at that.' I nod at the grey hoodie. 'Three years. They kept it three years. And you went. For coffee. Did you at least tell them you have someone who steals your hoodies now?'"
496 completion tokens (425 hidden reasoning_tokens) · $0.000581 / reply

Lab Take: When we capped completion at 220 tokens, V4.1 Flash returned a blank string because it burned all 220 tokens thinking to itself! Uncapped, it burned 425 reasoning tokens ($0.00058 vs $0.00005) to write a decent but choppy screenplay beat.

MythoMax 13B / Budget App BotGeneric Wrapper · 61.2 Slop
"*Raises an eyebrow, unimpressed* Oh, really? And why exactly did you decide to go out and grab coffee with your ex after all this time? You do realize how that might make me feel, right?"
65 completion tokens · 0 reasoning_tokens · $0.000018 / reply

Lab Take: Reads like a daytime soap opera script mixed with a therapy worksheet ("You do realize how that might make me feel"). Zero subtext.

Interactive EQ-Bench "AI Slop & Cliché" Detector (Paste Any Companion Reply)

Based on eqbench.com/slop-score.html trigram & contrast forensics
Detected Cliché Triggers:“shiver ran down”“voice barely a whisper”“breath caught in”“couldn't help but”“testament to”“unspoken”“Not X, but Y” LLM tic
Computed Slop Score: 99 / 100