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: no account, no sign up, just a card and a key (ou-...). Or hand your agent 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):

{
  "$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:

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 to the models block the same way. To see every id from the command line:

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

Check the key before you start

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	`deepseek-v4.1-flash-1017-uncensored`	2/5	100%	$1.65
#2	GLM 5.3 Flash Uncensored	`glm-5.3-flash-uncensored`	3/5	94%	$0.620
#3	Qwen 3.8 27B Uncensored Fast by Heabsy	`qwen3.8-27b-uncensored-fast`	2/5	100%	$3.45
#4	DeepSeek V4.1 Flash 0910 Uncensored	`deepseek-v4.1-flash-0910-uncensored`	2/5	97%	$1.65
#5	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	`glm-5.3-flash-apex-abliterated`	3/5	0%	$0.650
GLM 5.3 Flash Uncensored	`glm-5.3-flash-uncensored`	3/5	40%	$0.620
Gemma 4 31B Gembrain Uncensored Heretic	`gemma-4-31b-gembrain-uncensored-heretic`	3/5	40%	$0.612
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 lists every provider's cached price, and you can set your key to route by lowest cost on the credits page. 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
404	`model_not_found`	No model with that id	Copy the id from /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. The same setup works for Codex and Claude Code: guide.

How to add an uncensored model provider to OpenCode