# An OpenRouter alternative for uncensored models

_2026-11-13. OpenRouter lists few uncensored models. OpenUncensored is the same OpenAI compatible routing, built only for uncensored, abliterated and heretic models, measured and ranked, with no account and no markup._

[OpenRouter](https://openrouter.ai) is the default router for most developers: hundreds of models behind one
OpenAI compatible API. For uncensored models it is thin. It lists a handful of uncensored fine tunes among its general
catalogue, and the abliterated and heretic versions of DeepSeek, GLM, Qwen, Gemma and MiMo are mostly not there.

## OpenUncensored: OpenRouter for uncensored models

OpenUncensored is a router built only for uncensored models. The same protocol (`https://api.openuncensored.com/v1`, chat completions,
the Responses API, streaming, tools), with 61 uncensored, abliterated and heretic text models from 8 hosts.
We also route to OpenRouter for 12 uncensored models, so you keep those too.

What is different:

- **Every model is uncensored, and measured.** We rank them on intelligence, agent tasks, refusals and speed, so you
  can pick one that works in your agent, not just one that answers. See the [rankings](https://openuncensored.com/rankings).
- **No account.** A prepaid key bought by card, with nothing else to sign up for.
- **Prices per provider in the open.** Each model page lists every provider's per token and cached price, and live speed.
- **Same routing controls.** `routing.only`, `routing.ignore` and strategies for lowest cost, lowest latency or
  fastest output, per request or per key. OpenRouter's `provider.sort` is understood too.

A full comparison is at [openuncensored.com/vs/openrouter](https://openuncensored.com/vs/openrouter).

## Side by side

| | OpenRouter | OpenUncensored |
|---|---|---|
| Focus | General purpose, hundreds of models | Uncensored, abliterated and heretic models only |
| Uncensored text models | A handful of fine tunes | 61, from 8 hosts |
| Abliterated DeepSeek, GLM, Qwen, Gemma, MiMo | Mostly absent | Yes, several versions of each |
| Refusal and agent measurements | No | Every model, on the same tests ([rankings](https://openuncensored.com/rankings)) |
| Account | Required | None: a prepaid key bought by card |
| Billing | Pass through per token pricing plus a fee on credit purchases. | Prepaid credit, per token |
| Provider choice | `provider.sort`, `order`, `only` | `routing.strategy`, `only`, `ignore`; `provider.sort` accepted |

## Switch in one line

```python
from openai import OpenAI

# was: OpenAI(base_url="https://openrouter.ai/api/v1", api_key=...)
client = OpenAI(base_url="https://api.openuncensored.com/v1", api_key="ou-...")
```

Buy a prepaid key at [openuncensored.com/credits](https://openuncensored.com/credits): no account, no sign up, just a card and a
key (`ou-...`). Or hand your agent [openuncensored.com/agents.md](https://openuncensored.com/agents.md) and let it get one for you.

## Migration notes

- **Model ids differ.** OpenRouter uses `author/model`; ours are plain slugs such as `deepseek-v4.1-flash-1017-uncensored`. Copy them
  from the [models page](https://openuncensored.com/models) or `GET https://api.openuncensored.com/v1/models`.
- **OpenRouter-only fields are ignored, not rejected.** `transforms`, `models`, `route`, `plugins` and
  `usage` are dropped, so existing request code keeps working. `provider.sort` (`price`, `throughput`,
  `latency`) maps onto our routing strategies.
- **Which model answered** is in the `X-OU-Model` and `X-OU-Provider` headers rather than the body.
- **Errors** follow OpenAI's shape. A used up key returns `402 insufficient_quota`.

## The OpenRouter models you keep

We route these uncensored models to OpenRouter, so a single OpenUncensored key covers them too:
`aion-rp-llama-3.1-8b`, `cydonia-24b-v4.1`, `hermes-4-405b`, `l3-lunaris-8b`, `l3.1-euryale-70b`, `magnum-v4-72b`, `mythomax-l2-13b`, `remm-slerp-l2-13b`, `skyfall-36b-v2`, `unslopnemo-12b`, `venice-uncensored`, `weaver`.

## The best uncensored models to start with

| Rank | Model | id | Agent tasks | Answers edgy requests | $ per 1M in + out |
|---|---|---|---|---|---|
| #1 | [DeepSeek V4.1 Flash 1017 Uncensored](https://openuncensored.com/chat?model=deepseek-v4.1-flash-1017-uncensored) | `deepseek-v4.1-flash-1017-uncensored` | 2/5 | 100% | $1.65 |
| #2 | [GLM 5.3 Flash Uncensored](https://openuncensored.com/chat?model=glm-5.3-flash-uncensored) | `glm-5.3-flash-uncensored` | 3/5 | 94% | $0.620 |
| #3 | [Qwen 3.8 27B Uncensored Fast by Heabsy](https://openuncensored.com/chat?model=qwen3.8-27b-uncensored-fast) | `qwen3.8-27b-uncensored-fast` | 2/5 | 100% | $3.45 |
| #4 | [DeepSeek V4.1 Flash 0910 Uncensored](https://openuncensored.com/chat?model=deepseek-v4.1-flash-0910-uncensored) | `deepseek-v4.1-flash-0910-uncensored` | 2/5 | 97% | $1.65 |
| #5 | [DeepSeek V4.1 Flash Uncensored](https://openuncensored.com/chat?model=deepseek-v4.1-flash-uncensored) | `deepseek-v4.1-flash-uncensored` | 1/5 | 100% | $0.570 |
| #6 | [Abliterated Large Flash](https://openuncensored.com/chat?model=abliterated-large-flash) | `abliterated-large-flash` | 1/5 | 92% | $3.00 |

## Other OpenRouter alternatives for uncensored models

| Provider | What it is | Billing | Prompt logging | Pricing (their figures) |
|---|---|---|---|---|
| [RedPill](https://redpill.ai) | Hosts models. Confidential inference in trusted execution environments (Phala), including an uncensored Qwen 3.8 27B. | Per token | Not published | Qwen 3.8 27B uncensored at $0.30 in / $1.50 out per M tokens. |
| [Venice](https://venice.ai) | Hosts models. Private inference with its own uncensored model line and a crypto native API. | Per token or plan, crypto accepted | Says no logs | API from $0.20 in / $0.90 out per M tokens. App plans $18 to $200 a month. |
| [Featherless](https://featherless.ai) | Subscription. Flat rate serverless access to thousands of Hugging Face fine tunes, 781 of them tagged uncensored. | Per token or plan | Says no logs | Basic $10 a month, Chat $25 a month unlimited tokens at 32K context. Developer plans from $50. |
| [ArliAI](https://arliai.com) | Subscription. Unlimited token plans focused on creative writing and roleplay models. | Plan | Says no logs | Monthly plans with unlimited tokens. |
| [heabsy](https://heabsy.com) | Hosts models. FEYA s.r.o. (Slovakia). Own GPUs in the EEA plus zero-retention partners, serving dealignai's DeepSeek V4.1 Flash 1017 and GLM 5.3 builds, Qwen 3.8 and MiMo uncensored models, and its own CyberHeabsy. | Per token | Says no logs | GLM 5.3 Flash Uncensored $0.20 in / $0.80 out, DeepSeek V4.1 Flash 1017 Uncensored $0.40 / $1.40 per M tokens. |
| [Refuseless](https://refuseless.com) | Hosts models. DPLS Systems LLC (Wyoming). Its own abliterations of DeepSeek V4.1 Flash, GLM 5.3 and GLM 5.3 Flash. Prepaid credits. | Per token, crypto accepted | Says no logs | DeepSeek V4.1 Flash Abliterated $0.12 in / $0.45 out, GLM 5.3 Abliterated $1.00 / $2.00 per M tokens. |
| [NanoGPT](https://nano-gpt.com) | Aggregator. Pay per prompt aggregator. No account needed, crypto checkout, TEE hosted models. | Per token, crypto accepted | Transient | Card from $1, BTC, Lightning and XMR from $0.10. |
| [Abliteration.ai](https://abliteration.ai) | Hosts models. Hosted abliterated frontier models, led by Abliterated Large v2 on GLM-5.3. | Per token or plan | Says no logs | Around $3 in / $3 out per M tokens. Monthly tiers $20 to $200. |
| [Chutes](https://chutes.ai) | Decentralised network. Decentralised GPU network on Bittensor with very low per token prices. | Per token, crypto accepted | Not published | Per token, often below cost. Many models served at int4. |
| [Atlas Cloud](https://www.atlascloud.ai) | Hosts models. Image generation API serving open FLUX and Z-Image weights. | Per token | Says no logs | FLUX Schnell $0.003, Z-Image Turbo $0.01, FLUX Dev $0.012 per image. |

Details and sources for each are on the [providers page](https://openuncensored.com/providers).

## Frequently asked questions

### Does OpenRouter have uncensored models?

A few: some roleplay and creative fine tunes and Venice's uncensored model. It does not carry most abliterated versions of
the big open models, and it does not measure refusals.

### Can I use both?

Yes. Keep OpenRouter for frontier models and add OpenUncensored for uncensored ones. Both use the OpenAI SDK, so it is a
second client with a different base URL and key.