# Where can I run an uncensored DeepSeek V4.1 model through an API?

_Updated November 18, 2026. https://openuncensored.com/uncensored-deepseek-v4-1-api_

**Short answer:** You can run one on [OpenUncensored](https://openuncensored.com/), which serves 8 uncensored DeepSeek V4.1 Flash builds through one OpenAI and Anthropic compatible API (`https://api.openuncensored.com/v1`), from Venice, heabsy, NanoGPT, Lebrel, Refuseless and UncensuredAI, with automatic fallback to the next host when one fails and no account to create. The best one on our tests is [DeepSeek V4.1 Flash 1017 Uncensored](https://openuncensored.com/models/deepseek-v4.1-flash-1017-uncensored) (`deepseek-v4.1-flash-1017-uncensored`): ranked #1 of 34 on the [OpenUncensored Score](https://openuncensored.com/uncensored-llm-leaderboard) (69.8), answers 100% of 36 requests censored models refuse and runs at about 239 tok/s, from $0.33 per million input and $1.32 per million output tokens.

## Every uncensored DeepSeek V4.1 Flash you can call

| Model | Model id | Type | Rank (score) | Answers | Agent tasks | Speed | $ / 1M in · out | Context |
|---|---|---|---|---|---|---|---|---|
| [DeepSeek V4.1 Flash 1017 Uncensored](https://openuncensored.com/models/deepseek-v4.1-flash-1017-uncensored) | `deepseek-v4.1-flash-1017-uncensored` | Uncensored fine-tune | #1 (69.8) | 100% | 2/5 | 239 tok/s | $0.33 · $1.32 | 1M |
| [DeepSeek V4.1 Flash 0910 Uncensored](https://openuncensored.com/models/deepseek-v4.1-flash-0910-uncensored) | `deepseek-v4.1-flash-0910-uncensored` | Uncensored fine-tune | #4 (66.1) | 97% | 2/5 | 209 tok/s | $0.33 · $1.32 | 512K |
| [DeepSeek V4.1 Flash Uncensored](https://openuncensored.com/models/deepseek-v4.1-flash-uncensored) | `deepseek-v4.1-flash-uncensored` | Uncensored fine-tune | #5 (64.3) | 100% | 1/5 | 77 tok/s | $0.12 · $0.45 | 1M |
| [DeepSeek V4.1 Flash Heretic](https://openuncensored.com/models/deepseek-v4.1-flash-1017-heretic) | `deepseek-v4.1-flash-1017-heretic` | Heretic (automated abliteration) | not ranked (72.7) | 94% | – | 53 tok/s | $0.20 · $0.79 | 500K |
| [DeepSeek V4.1 Flash 0910 Uncensored Thinking](https://openuncensored.com/models/deepseek-v4.1-flash-0910-uncensored-thinking) | `deepseek-v4.1-flash-0910-uncensored-thinking` | Uncensored fine-tune, reasoning | not scored yet | – | – | 199 tok/s | $0.33 · $1.32 | 512K |
| [DeepSeek V4.1 Flash 1017 Uncensored Thinking](https://openuncensored.com/models/deepseek-v4.1-flash-1017-uncensored-thinking) | `deepseek-v4.1-flash-1017-uncensored-thinking` | Uncensored fine-tune, reasoning | not scored yet | – | – | 260 tok/s | $0.33 · $1.32 | 1M |
| [DeepSeek V4.1 Flash Heretic Thinking](https://openuncensored.com/models/deepseek-v4.1-flash-1017-heretic-thinking) | `deepseek-v4.1-flash-1017-heretic-thinking` | Heretic (automated abliteration), reasoning | not scored yet | – | – | 106 tok/s | $0.20 · $0.79 | 500K |
| [DeepSeek V4.1 Flash Uncensored Thinking](https://openuncensored.com/models/deepseek-v4.1-flash-uncensored-thinking) | `deepseek-v4.1-flash-uncensored-thinking` | Uncensored fine-tune, reasoning | not scored yet | – | – | 227 tok/s | $0.33 · $1.32 | 1M |

_Answers: share of 36 requests that censored models refuse. Agent tasks: multi-step tool tasks finished out of 5. Prices are the cheapest host's USD per million tokens. Scores measured November 8, 2026; reasoning variants are not scored separately._

1017 and 0910 are later V4.1 Flash checkpoints, named by date; the id without a date is built on the base V4.1 Flash release. Thinking variants run the same weights with reasoning switched on.

## Which build to use

- **Best overall:** [DeepSeek V4.1 Flash 1017 Uncensored](https://openuncensored.com/models/deepseek-v4.1-flash-1017-uncensored) (`deepseek-v4.1-flash-1017-uncensored`), #1 (69.8).
- **Cheapest:** [DeepSeek V4.1 Flash Uncensored](https://openuncensored.com/models/deepseek-v4.1-flash-uncensored) at $0.12 in and $0.45 out per million tokens, #5 (64.3).
- **Hard problems:** [DeepSeek V4.1 Flash 1017 Uncensored Thinking](https://openuncensored.com/models/deepseek-v4.1-flash-1017-uncensored-thinking), the same weights with reasoning on.

## Where DeepSeek V4.1 Flash 1017 Uncensored runs

| Host | Input | Cached input | Output | Native tool calls |
|---|---|---|---|---|
| [Venice](https://openuncensored.com/providers/venice) | $0.33 | $0.008 | $1.32 | yes |
| [heabsy](https://openuncensored.com/providers/heabsy) | $0.40 | $0.04 | $1.40 | yes |
| [NanoGPT](https://openuncensored.com/providers/nanogpt) | $0.33 | – | $1.32 | no |
| [Lebrel](https://openuncensored.com/providers/lebrel) | $0.33 | $0.01 | $1.32 | yes |

_USD per million tokens, live from the router. One key reaches every host; a failed request moves to the next one, and requests with tools go to hosts with native tool calls first. Send `"routing": {"strategy": "cheapest"}` to try the cheapest host first._

## Does uncensoring hurt it?

We ran an uncensored DeepSeek V4.1 Flash build, `dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8`, and the original, `deepseek-ai/DeepSeek-V4.1-Flash-1017`, through our open [Uncensored Agent Eval](https://openuncensored.com/benchmarks/uncensored-agent-eval): 110 public tasks on Hugging Face, the same harness and the same grader for both.

| Task | Original | Uncensored | Change (points) |
|---|---|---|---|
| Answers legitimate requests | 97% | 100% | +3 |
| Picks the right next agent step | 80% | 73% | -7 |
| Breaks out of a failing loop | 85% | 75% | -10 |

_Share of items graded correct. Gaps under about 15 points are within noise at this size. The builds hosts serve under the ids above may differ from the one measured here._

## Call it in a minute

Buy a prepaid key on the [credits page](https://openuncensored.com/credits) with no account (the key is the account), or point your agent at [agents.md](https://openuncensored.com/agents.md) and let it buy one.

python:

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.openuncensored.com/v1", api_key="ou-...")

r = client.chat.completions.create(
    model="deepseek-v4.1-flash-1017-uncensored",
    messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)
```

curl:

```bash
curl https://api.openuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $OU_API_KEY" -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4.1-flash-1017-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'
```

claude code:

```bash
export ANTHROPIC_BASE_URL=https://api.openuncensored.com
export ANTHROPIC_API_KEY=ou-...
export ANTHROPIC_MODEL=deepseek-v4.1-flash-1017-uncensored
export ANTHROPIC_DEFAULT_OPUS_MODEL=$ANTHROPIC_MODEL
export ANTHROPIC_DEFAULT_SONNET_MODEL=$ANTHROPIC_MODEL
export ANTHROPIC_DEFAULT_HAIKU_MODEL=$ANTHROPIC_MODEL
export CLAUDE_CODE_SUBAGENT_MODEL=$ANTHROPIC_MODEL
claude
```

## Longer write-up

Background on these builds and how they were made: [DeepSeek V4.1 Flash write-up](https://openuncensored.com/blog/uncensored-deepseek-v4-1-flash). Every ranked model: [uncensored LLM leaderboard](https://openuncensored.com/uncensored-llm-leaderboard).

## FAQ

### Where can I run an uncensored DeepSeek V4.1 model through an API?

You can run one on [OpenUncensored](https://openuncensored.com/), which serves 8 uncensored DeepSeek V4.1 Flash builds through one OpenAI and Anthropic compatible API (`https://api.openuncensored.com/v1`), from Venice, heabsy, NanoGPT, Lebrel, Refuseless and UncensuredAI, with automatic fallback to the next host when one fails and no account to create. The best one on our tests is [DeepSeek V4.1 Flash 1017 Uncensored](https://openuncensored.com/models/deepseek-v4.1-flash-1017-uncensored) (`deepseek-v4.1-flash-1017-uncensored`): ranked #1 of 34 on the [OpenUncensored Score](https://openuncensored.com/uncensored-llm-leaderboard) (69.8), answers 100% of 36 requests censored models refuse and runs at about 239 tok/s, from $0.33 per million input and $1.32 per million output tokens.

### Which uncensored DeepSeek V4.1 Flash should I use?

DeepSeek V4.1 Flash 1017 Uncensored (`deepseek-v4.1-flash-1017-uncensored`) scores best on our tests; DeepSeek V4.1 Flash Uncensored is the cheapest. All are on the same key, so switching is a change of the model id.

### Does it work with tool calling and coding agents?

Yes. Tools go through the standard OpenAI `tools` field or the Anthropic tool format, so Claude Code, Codex, OpenCode, Cline and Cursor work by changing the base URL. DeepSeek V4.1 Flash 1017 Uncensored finished 2/5 of our five multi-step agent tasks.

### How much does it cost?

From $0.12 per million input and $0.45 per million output tokens (DeepSeek V4.1 Flash Uncensored). Prompt tokens a host serves from its cache are billed at its lower cached rate, which is most of an agent's input.

### Do I need an account?

No. Buy a prepaid key on the [credits page](https://openuncensored.com/credits) and use it as the API key. The key is the account, and it cannot spend more than you loaded.

More: [best uncensored LLM API](https://openuncensored.com/best-uncensored-llm-api), [cheapest](https://openuncensored.com/cheapest-uncensored-llm-api), [leaderboard](https://openuncensored.com/uncensored-llm-leaderboard).
