One API for uncensored and abliterated models.
Pay for the tokens your product uses.
Every request, its tokens, cost, and outcome.
| Model | Requests | Spend |
|---|---|---|
| glm-5.3-abliterated | 6 | $0.002304 |
| deepseek-v4.1-flash-1017-abliterated | 0 | $0.00 |
| Total | 6 | $0.002304 |
Usage metadata, without the conversation.
| Time | Status | Model | Request ID |
|---|---|---|---|
| 00:59 | 200 | glm-5.3-abliterated | preview_006 |
| 00:56 | 200 | glm-5.3-abliterated | preview_005 |
| 00:53 | 200 | glm-5.3-abliterated | preview_004 |
| 00:50 | 200 | glm-5.3-abliterated | preview_003 |
| 00:47 | 200 | glm-5.3-abliterated | preview_002 |
| 00:44 | 200 | glm-5.3-abliterated | preview_001 |
curl https://api.yourdomain.com/v1/chat/completions \
-H "Authorization: Bearer $UNCENSOREDLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"glm-5.3-abliterated", "messages":[{"role":"user","content":"Hello"}]}'Keep your OpenAI client. Change the base URL, use your key, and choose an approved model.
base_url = "https://api.yourdomain.com/v1"
api_key = os.environ["UNCENSOREDLABS_API_KEY"]Streaming chat completions, with the same endpoint your existing client expects.
data: {"choices":[{"delta":{"content":"…"}}]}data: {"usage":{}}data: [DONE]Check context, capabilities, and per-token rates before you switch. Unknown measurements stay unknown.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| glm-5.3-abliterated | $2.00 | $2.00 |
| deepseek-v4.1-flash-1017-abliterated | $0.30 | $0.30 |
Prepay your credits. Set key limits. See the tokens and charge behind every request.
| Model | Context | Input / 1M | Cached / 1M | Output / 1M | Get access |
|---|---|---|---|---|---|
GLM-5.3 Abliteratedglm-5.3-abliterated | 1,000,000 | $2.000 | $0.600 | $2.000 | Get access |
DeepSeek V4.1 Flash 1017 Abliterateddeepseek-v4.1-flash-1017-abliterated | 1,000,000 | $0.300 | $0.160 | $0.300 | Get access |
One API key for your approved models, streaming, key spending limits, model allowlists, and usage accounting.
Prices are snapshotted per request. Actual usage settles the final charge. Uncertain usage stays reserved for reconciliation.
Point your OpenAI SDK at UncensoredLabs.
Use your key and an approved model ID.
We don’t store your prompts or model responses on our application servers. The inference provider’s retention policy applies.
curl https://api.yourdomain.com/v1/chat/completions \
-H "Authorization: Bearer $UNCENSOREDLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3-abliterated",
"messages": [{"role": "user", "content": "Hello, world."}],
"max_tokens": 256,
"stream": true
}'Create an account, add prepaid credits, and generate an API key. Set your OpenAI client’s base URL to your UncensoredLabs API domain and choose a model from the approved catalog.
Input, cached input, and output have separate published rates. A request reserves a conservative maximum, then settles against verified usage at its original price. Unused reserved credit is released.
Our application does not store conversation content. We retain usage and financial metadata. Cloudflare and the inference provider process requests, and the provider may archive content under its own policy.
Only verified uncensored or abliterated variants are enabled. Development fixtures are labelled as mocks. We do not publish invented availability, speed, or uptime figures.
Live access remains disabled until provider resale authorization, credentials, payment configuration, and launch checks are confirmed. The local development environment uses mock inference and test credits.
Create an account. Choose your model.
Connect your application.