# How to add an uncensored model provider to OpenCode

_2026-11-13. Add OpenUncensored to OpenCode as an OpenAI compatible provider in one opencode.json block, pick a model that works in agents, and avoid the daemon environment gotcha._

OpenCode can use any OpenAI compatible provider, so adding uncensored models takes one block of config. With
OpenUncensored as the provider you get 61 uncensored, abliterated and heretic models behind one key, and you can switch
between them per run.

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.

## Add the provider

In `opencode.json` in your project, or `~/.config/opencode/opencode.json` for every project (OpenCode 2):

```json
{
  "$schema": "https://opencode.ai/config.json",
  "providers": {
    "openuncensored": {
      "name": "OpenUncensored",
      "env": ["OPENUNCENSORED_API_KEY"],
      "package": "@opencode/ai/providers/openai-compatible",
      "settings": { "baseURL": "https://api.openuncensored.com/v1" },
      "models": {
        "deepseek-v4.1-flash-1017-uncensored": { "name": "DeepSeek V4.1 Flash 1017 Uncensored" },
        "glm-5.3-flash-uncensored": { "name": "GLM 5.3 Flash Uncensored" },
        "qwen3.8-27b-uncensored-fast": { "name": "Qwen 3.8 27B Uncensored Fast by Heabsy" }
      }
    }
  }
}
```

Then:

```bash
export OPENUNCENSORED_API_KEY=ou-...
opencode run -m openuncensored/deepseek-v4.1-flash-1017-uncensored "Explain this repository"
```

Add any model id from the [models page](https://openuncensored.com/models) to the `models` block the same way. To see every id from the
command line:

```bash
curl -s https://api.openuncensored.com/v1/models | jq -r '.data[].id'
```

## Check the key before you start

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

If this works and OpenCode does not, the problem is in the config or the environment OpenCode runs in.

## Gotchas

- **The background daemon does not see your shell.** `opencode serve` started as a service does not read variables
  you exported later. Put the key where the daemon reads it, or test with `opencode run --standalone`.
- **Older OpenCode versions** use a `provider` block with `npm: "@ai-sdk/openai-compatible"` and
  `options.baseURL`. The base URL and model ids are the same.
- **Model names are prefixed** with the provider key: `openuncensored/<model id>`.

## Which model to pick

These are the strongest uncensored models on our tests right now, including five multi-step agent tasks:

| 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 |

For long agent sessions, favour the agent column: a model that loops burns tokens without progress. The best agents
right now:

| Model | id | Agent tasks | Loops | $ per 1M in + out |
|---|---|---|---|---|
| [Apex Flash 1 Abliterated](https://openuncensored.com/chat?model=glm-5.3-flash-apex-abliterated) | `glm-5.3-flash-apex-abliterated` | 3/5 | 0% | $0.650 |
| [GLM 5.3 Flash Uncensored](https://openuncensored.com/chat?model=glm-5.3-flash-uncensored) | `glm-5.3-flash-uncensored` | 3/5 | 40% | $0.620 |
| [Gemma 4 31B Gembrain Uncensored Heretic](https://openuncensored.com/chat?model=gemma-4-31b-gembrain-uncensored-heretic) | `gemma-4-31b-gembrain-uncensored-heretic` | 3/5 | 40% | $0.612 |
| [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 | 0% | $1.65 |

## What it costs in an agent

OpenCode resends the conversation at every step, so cached input dominates the bill. Each [model page](https://openuncensored.com/models)
lists every provider's cached price, and you can set your key to route by lowest cost on the
[credits page](https://openuncensored.com/credits#routing). A prepaid key cannot spend more than you loaded.

## Errors you may see

| Status | Code | What it means | What to do |
|---|---|---|---|
| 401 | `invalid_api_key` | Missing or wrong key | Send `Authorization: Bearer ou-...` |
| 402 | `insufficient_quota` | The key's credit is used up | Top up the same key at [/credits](https://openuncensored.com/credits) |
| 404 | `model_not_found` | No model with that id | Copy the id from [/models](https://openuncensored.com/models) or `GET https://api.openuncensored.com/v1/models` |
| 400 | `invalid_routing_options` | `only`/`ignore` exclude every provider, or an unknown strategy | Loosen the routing block |
| 4xx | `upstream_rejected_request` | The provider rejected the request itself | Read the message: usually a parameter that model does not support |
| 429 | `rate_limit_exceeded` | Every provider for the model is rate limited | Retry after the `Retry-After` header |
| 502 | `all_providers_failed` | Every provider was tried and failed | Retry, or pick another model |

The full table is on the [rankings page](https://openuncensored.com/rankings). The same setup works for Codex and Claude Code:
[guide](https://openuncensored.com/blog/uncensored-model-claude-code-codex).