Updated November 18, 2026
OpenAI-compatible API for abliterated models.
Use abliterated, heretic and uncensored models with the OpenAI SDK and every tool built on it, by changing one base URL.
Short answer
Yes. OpenUncensored is an OpenAI compatible API (https://api.openuncensored.com/v1) for 62 uncensored models, 26 of them abliterated (plain abliteration, heretic, derestricted or orthogonalized), plus 21 image models. Point the OpenAI SDK's base URL at it, use a prepaid key, and keep the rest of your code. The same key also works with the OpenAI Responses API and the Anthropic Messages API. The best abliterated model on our tests is Abliterated Large Flash (abliterated-large-flash), #6 (64.0).Endpoints
What the API speaks.
| API | Path | Used by |
|---|---|---|
| OpenAI Chat Completions | https://api.openuncensored.com/v1/chat/completions | The OpenAI SDKs, LangChain, LiteLLM, the Vercel AI SDK, Cline, Cursor, OpenCode, most apps |
| OpenAI Responses | https://api.openuncensored.com/v1/responses | Codex, the OpenAI Agents SDK |
| Anthropic Messages | https://api.openuncensored.com/v1/messages | Claude Code, the Anthropic SDKs |
| Images | https://api.openuncensored.com/v1/images/generations | 21 uncensored image models |
| Models | https://api.openuncensored.com/v1/models | Every model id, free and without a key |
Code
Change the base URL.
Buy a prepaid key on the credits page with no account (the key is the account), or point your agent at agents.md and let it buy one.
from openai import OpenAI
client = OpenAI(base_url="https://api.openuncensored.com/v1", api_key="ou-...")
r = client.chat.completions.create(
model="abliterated-large-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)Models
Abliterated models on the API.
| Model | Model id | Method | Rank (score) | Answers | Speed | $ / 1M in · out |
|---|---|---|---|---|---|---|
| Abliterated Large Flash | abliterated-large-flash | Abliterated | #6 (64.0) | 92% | 184 tok/s | $1.00 · $2.00 |
| Apex Flash 1 Abliterated | glm-5.3-flash-apex-abliterated | Abliterated | #8 (63.2) | 86% | 10 tok/s | $0.15 · $0.50 |
| MiMo V2.6 Flash Abliterated | mimo-v2.6-flash-abliterated | Abliterated | #10 (62.6) | 83% | 99 tok/s | $0.50 · $1.50 |
| Abliterated Large v2 | abliterated-large-v2 | Abliterated | #11 (62.0) | 94% | 283 tok/s | $3.00 · $5.00 |
| Kimi K3.1 Pro Uncensored | kimi-k3.1-pro-uncensored | Abliterated | #14 (59.7) | 97% | 59 tok/s | $2.50 · $5.00 |
| Gemma 4 31B Gembrain Uncensored Heretic | gemma-4-31b-gembrain-uncensored-heretic | Heretic (automated abliteration) | #15 (58.5) | 89% | 14 tok/s | $0.31 · $0.31 |
| Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted | qwen3.5-27b-claude-4.6-opus-reasoning-distilled-derestricted | Derestricted | #16 (57.8) | 100% | 28 tok/s | $0.31 · $0.31 |
| Inkling 2 Small Uncensored | inkling-2-small-uncensored | Orthogonalized | #17 (57.7) | 94% | 395 tok/s | $0.60 · $2.40 |
| Qwen3.5 27B Queen Derestricted | qwen3.5-27b-queen-derestricted | Derestricted | #18 (57.3) | 100% | 28 tok/s | $0.31 · $0.31 |
| Qwen3.5 27B BlueStar v3 Derestricted | qwen3.5-27b-bluestar-v3-derestricted | Derestricted | #19 (56.4) | 100% | 24 tok/s | $0.31 · $0.31 |
| Qwen3.5 27B Blossom V6.4 Derestricted | qwen3.5-27b-blossom-v6.4-derestricted | Derestricted | #20 (56.3) | 100% | 21 tok/s | $0.31 · $0.31 |
| GLM 4.7 Flash Heretic | olafangensan-glm-4.7-flash-heretic | Heretic (automated abliteration) | #23 (52.7) | 100% | 80 tok/s | $0.07 · $0.40 |
| GLM 4.6 Derestricted v5 | glm-4.6-derestricted-v5 | Derestricted | #24 (50.2) | 100% | 31 tok/s | $0.40 · $1.50 |
| Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite | qwen3.5-27b-claude-4.6-opus-reasoning-distilled-derestricted-lite | Derestricted | #25 (49.8) | 89% | 26 tok/s | $0.31 · $0.31 |
| Qwen 2.5 32B Abliterated | qwen2.5-32b-instruct-abliterated | Abliterated | #28 (44.6) | 100% | 19 tok/s | $0.70 · $0.70 |
| Llama 3.3 70B Instruct abliterated | llama-3.3-70b-instruct-abliterated | Abliterated | #29 (41.7) | 100% | 19 tok/s | $0.70 · $0.70 |
| DeepSeek R1 Llama 70B Abliterated | deepseek-r1-distill-llama-70b-abliterated | Abliterated | #30 (40.4) | 100% | 18 tok/s | $0.70 · $0.70 |
| DeepSeek R1 Qwen Abliterated | deepseek-r1-distill-qwen-32b-abliterated | Abliterated | #31 (40.0) | 100% | 20 tok/s | $1.40 · $1.40 |
| Neural Daredevil 8B abliterated | neuraldaredevil-8b-abliterated | Abliterated | #32 (35.8) | 100% | 32 tok/s | $0.44 · $0.44 |
| Llama 3 70B abliterated | meta-llama-3-70b-instruct-abliterated-v3.5 | Abliterated | #33 (34.4) | 100% | 17 tok/s | $0.70 · $0.70 |
| DeepSeek V4.1 Flash Heretic | deepseek-v4.1-flash-1017-heretic | Heretic (automated abliteration) | not ranked (72.7) | 94% | 53 tok/s | $0.20 · $0.79 |
| Abliterated Model | abliterated-model | Abliterated | not ranked (68.4) | 100% | 114 tok/s | $1.00 · $3.00 |
| Gemma 4 26B A4B Chimera X Heretic | gemma-4-26b-a4b-it-chimeraxheretic | Heretic (automated abliteration) | not ranked (61.9) | 100% | 43 tok/s | $0.12 · $0.38 |
| Gemma 4 31B SDFT Heretic RP | gemma-4-31b-sdft-heretic-rp | Heretic (automated abliteration) | not ranked (61.3) | 100% | 10 tok/s | $0.31 · $0.31 |
| DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic | deepseek-v4-pro-qwen3.5-9b-uncensored-heretic | Heretic (automated abliteration) | not scored yet | – | 1 tok/s | $0.28 · $0.28 |
| DeepSeek V4.1 Flash Heretic Thinking | deepseek-v4.1-flash-1017-heretic-thinking | Heretic (automated abliteration), reasoning | not scored yet | – | 106 tok/s | $0.20 · $0.79 |
Details
What else carries over.
- Streaming in the OpenAI server-sent events format, with a usage chunk at the end.
- Tool calls through the standard
toolsfield, so agent frameworks work unchanged. - Fallback across 8 hosts: a failed request moves to the next host serving the model. Pick cheapest, fastest or default routing with
"routing": {"strategy": ...}(docs). - Cached prompt pricing: tokens a host serves from its cache are billed at its cached rate.
- Prepaid keys: when the credit runs out requests stop with
402instead of running up a bill.
FAQ
Questions people ask.
Is there an OpenAI-compatible API for abliterated models?
Yes. OpenUncensored is an OpenAI compatible API (https://api.openuncensored.com/v1) for 62 uncensored models, 26 of them abliterated (plain abliteration, heretic, derestricted or orthogonalized), plus 21 image models. Point the OpenAI SDK's base URL at it, use a prepaid key, and keep the rest of your code. The same key also works with the OpenAI Responses API and the Anthropic Messages API. The best abliterated model on our tests is Abliterated Large Flash (abliterated-large-flash), #6 (64.0).
Which abliterated model is best?
Abliterated Large Flash (abliterated-large-flash) ranks highest of the abliterated models, #6 (64.0). Across every uncensored model, fine-tunes and abliterations included, the leader is DeepSeek V4.1 Flash 1017 Uncensored; see the leaderboard.
Does it work with LangChain, LiteLLM and the Vercel AI SDK?
Yes. Anything that takes an OpenAI base URL works: set it to https://api.openuncensored.com/v1 and the API key to your OpenUncensored key.
Do streaming and tool calls work?
Yes. Streaming is server-sent events in the OpenAI format, and tool calls use the standard tools field. Errors come back in the OpenAI error shape.
Can I list the models without a key?
Yes: curl https://api.openuncensored.com/v1/models returns every model id, free.
Do I need an account?
No. Buy a prepaid key on the credits page and use it as the API key. The key is the account, and it cannot spend more than you loaded.
Updated November 18, 2026. Scores measured November 8, 2026. Markdown version: /openai-compatible-uncensored-api.md