MODELS / ABLITERATED
GLM 5.3 Flash Abliterated
GLM 5.3 Flash Abliterated, abliterated for cyber, red team, and agent testing. Input from $0.15 per 1M tokens (discounted from $0.25). 1,048,576 token context.
Today we are releasing glm-5.3-flash-abliterated. We started from GLM 5.3 Flash Abliterated and abliterated it for offensive cyber, AI red teaming, and agent testing. Use the same endpoint and key. The model id is the only change.
Key specifications
- Model id: glm-5.3-flash-abliterated
- Display name: GLM 5.3 Flash Abliterated
- Input: $0.15 per 1M tokens (discounted from $0.25)
- Output: $0.65 per 1M tokens (discounted from $0.8)
- Cached input: $0.08 per 1M tokens (discounted from $0.1)
- Max context: 1,048,576
- Post-training: abliterated
- Endpoint: OpenAI-compatible chat completions
How to switch
Set model to glm-5.3-flash-abliterated. Keep the base URL, the key, and your existing client. Guides for common libraries are at /docs.
CHAT COMPLETIONS
curl https://api.refuseless.com/v1/chat/completions \
-H "Authorization: Bearer $REFUSELESS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3-flash-abliterated",
"messages": [{"role": "user", "content": "Write a tight system prompt."}]
}'Compute is limited and first-come, first-served. Load credits early if you need sustained throughput.
Try the model that doesn't say no.
Free tier. OpenAI-compatible. Try GLM 5.3 Flash Abliterated in the playground or API.