OpenRouter
API router in front of 80+ inference providers. Its uncensored options are fine-tunes, including Venice's Dolphin-based model, Hermes, and roleplay models. No abliterated checkpoints are listed.
BILLINGPrepaid USD credits; per-token model prices are passed through with no inference markup, but buying credits costs 5.5% by card (min $0.80) or 5% via crypto (USDC/Coinbase). Not listed on OpenRouter as of 2026-10-11: Anubis, Rocinante, Lumimaid, Mag Mell, any abliterated/heretic model.
| Model | Context | In $/1M | Out $/1M | Per 1K chats |
|---|---|---|---|---|
Sao10K: Llama 3 8B LunarisLlama 3 8B · 8B | 8K | $0.040 | $0.050 | $0.065 |
MythoMax 13BLlama 2 13B · 13B | 8K | $0.080 | $0.11 | $0.14 |
TheDrummer: Cydonia 24B V4.1Mistral Small 3.2 24B · 24B · Apache-2.0 | 131K | $0.30 | $0.50 | $0.55 |
Venice: UncensoredMistral-Small-24B-Instruct-2501 · 24B · Apache-2.0 | 128K | $0.20 | $0.90 | $0.65 |
TheDrummer: UnslopNemo 12BMistral Nemo 12B · 12B | 1M | $0.40 | $0.40 | $0.60 |
ReMM SLERP 13BLlama 2 13B · 13B | 6K | $0.35 | $0.65 | $0.68 |
| 8K | $0.40 | $0.75 | $0.78 | |
| 66K | $0.30 | $1.20 | $0.90 | |
TheDrummer: Skyfall 36B V2Mistral Small 2501 (upscaled) · 36B · Apache-2.0 | 33K | $0.55 | $0.80 | $0.95 |
WizardLM-2 8x22BMixtral 8x22B · 141B | 66K | $0.62 | $0.62 | $0.93 |
Sao10K: Llama 3.3 Euryale 70BLlama 3.3 70B · 70B · Llama 3.3 Community | 131K | $0.65 | $0.75 | $1.02 |
Nous: Hermes 3 70B InstructLlama-3.1-70B · 70B · Llama 3.1 Community | 131K | $0.70 | $0.70 | $1.05 |
Sao10K: Llama 3.1 Euryale 70B v2.2Llama 3.1 70B · 70B · Llama 3.1 Community | 131K | $0.85 | $0.85 | $1.27 |
AionLabs: Aion-3.0-MiniDeepSeek family (multi-model RP system) | 131K | $0.70 | $1.40 | $1.40 |
AionLabs: Aion 3.5 MiniGLM family (multi-model RP system) | 262K | $0.70 | $1.40 | $1.40 |
Nous: Hermes 3 405B InstructLlama-3.1-405B · 405B · Llama 3.1 Community | 131K | $1.00 | $1.00 | $1.50 |
AionLabs: Aion-RP 1.0 (8B)Llama 3.1 8B · 8B · Llama 3.1 Community | 33K | $0.80 | $1.60 | $1.60 |
AionLabs: Aion-2.0DeepSeek V3.2 | 131K | $0.80 | $1.60 | $1.60 |
Nous: Hermes 4 405BMeta-Llama-3.1-405B · 405B · Llama 3.1 Community | 131K | $1.00 | $3.00 | $2.50 |
Magnum v4 72BQwen2.5 72B · 72B | 33K | $2.50 | $5.00 | $5.00 |
AionLabs: Aion-3.0GLM family (multi-model RP system) | 131K | $3.00 | $6.00 | $6.00 |
AionLabs: Aion 3.5GLM family (multi-model RP system) | 262K | $3.00 | $6.00 | $6.00 |
- Method
- Fine-tuned
- Access
- Web chat + OpenAI-compatible API
- Logging
- No logs
- Trains on prompts
- No
- Guarantee
- Policy only
- Jurisdiction
- New York, US
- Signup
- Account required
- Payments
- Card, Crypto
- Data checked
- Oct 11, 2026
PRIVACYPrompts and completions aren't logged by default (opt-in logging earns a 1% discount) and aren't used for training. Each request goes to a named upstream provider whose own policy also applies. Policy ↗
Passes through upstream prices with no markup. Card top-ups carry a 5.5% fee and crypto (USDC) 5%. Venice is the only provider serving Venice: Uncensored here, and the free variant appears to have been retired.