ZHIPU GLM / TEXT
GLM-5.3 Abliterated API pricing
From $1.40 in / $1.40 out per 1M tokens
GLM-5.3 Abliterated costs $1.40 per 1M input tokens and $1.40 per 1M output tokens (cached input $0.40). Call it with model ID glm-5.3-abliterated at https://api.outrun.to/v1 using one prepaid Outrun key. Prices as of October 30, 2026.
USD / 1M TOKENS
How much does GLM-5.3 Abliterated cost per 1M tokens?
Main ID · Standard
| Token type | Outrun |
|---|---|
| Input | $1.40 |
| Cached input | $0.40 |
| Cache write | $1.40 |
| Output | $1.40 |
Route 2 · Standard
| Token type | Outrun |
|---|---|
| Input | $4.50 |
| Cached input | $1.32 |
| Output | $4.50 |
Billed prices, rounded up to the cent. Prices as of October 30, 2026.
Which GLM-5.3 Abliterated routes can I use?
GLM-5.3 Abliterated has 2 model IDs. Each route is its own ID with its own prices and setup; your key, base URL and request format stay the same. The main ID is the lowest-priced. The table shows each route's price and setup values.
| Model ID | Input | Output | Cached input | Setup |
|---|---|---|---|---|
Main IDglm-5.3-abliterated | $1.40 | $1.40 | $0.40 | Tools: Yes · Streaming: Yes · Reasoning: Yes · Image input: No · Context: 1,000,000 · Max output: 130,000 |
Route 2 of GLM-5.3 Abliterated: glm-5.3-abliterated-2Route 2 | $4.50 | $4.50 | $1.32 | Tools: Yes · Streaming: Yes · Reasoning: Yes · Image input: No · Context: 1,000,000 · Max output: 130,000 |
- Context window
- 1,000,000 tokens
- Max output
- 130,000 tokens
- Input
- Text
What is GLM-5.3 Abliterated?
GLM-5.3 Abliterated is a text model in the Outrun catalog. The base model is GLM-5.3. The standard rate is $1.40 in / $1.40 out per 1M tokens. It has 2 route IDs with their own prices; compare them above.
What does abliterated mean?
Abliterated models have their refusal behaviour removed from the model weights. Behaviour and quality differ by model, so test the one you choose.
Use of GLM-5.3 Abliterated is subject to the acceptable use terms in the Outrun Terms of Service.
What are the GLM-5.3 Abliterated model details?
| Model detail | Value |
|---|---|
| Developer | Zhipu AI |
| Base model | GLM-5.3 |
| Kind | Text |
| Licence | GLM-5.3 License (base model) |
How do I call GLM-5.3 Abliterated?
Use your Outrun key and the exact model ID. Requests use prepaid USD credit.
curl https://api.outrun.to/v1/chat/completions \
-H "Authorization: Bearer $OUTRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3-abliterated",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"max_tokens": 8192
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.outrun.to/v1",
api_key=os.environ["OUTRUN_API_KEY"],
)
reply = client.chat.completions.create(
model="glm-5.3-abliterated",
messages=[{"role": "user", "content": "Hello!"}],
max_tokens=8192,
)
print(reply.choices[0].message.content)Which tools work with GLM-5.3 Abliterated?
Any client that accepts an OpenAI-compatible base URL and a model ID can use glm-5.3-abliterated. Setup guides: Roo Code for uncensored models, Cline (OpenAI Compatible), OpenCode, SillyTavern, LiteLLM.
Main ID · glm-5.3-abliterated
Use these setup values for this model ID. Recommended output settings can be lower than the route maximum.
| Set this value | Value |
|---|---|
| API format | OpenAI compatible |
| Base URL | https://api.outrun.to/v1 |
| Model ID | glm-5.3-abliterated |
| Context window | 1,000,000 |
| Max output setting | 8,192 |
| Temperature | 1 |
| Streaming | Yes |
| Image support | No |
| R1 format | No |
| Include max tokens | Yes |
| Reasoning override | No |
| Prompt caching setting | No |
| Capability | Supported |
|---|---|
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning | Yes |
| Parallel tools | Yes |
| Image input | No |
| Roo Code ready | Yes |
Route 2 · glm-5.3-abliterated-2
Use these setup values for this model ID. Recommended output settings can be lower than the route maximum.
| Set this value | Value |
|---|---|
| API format | OpenAI compatible |
| Base URL | https://api.outrun.to/v1 |
| Model ID | glm-5.3-abliterated-2 |
| Context window | 1,000,000 |
| Max output setting | 8,192 |
| Streaming | No |
| Image support | No |
| R1 format | No |
| Include max tokens | Yes |
| Reasoning override | No |
| Prompt caching setting | No |
| Capability | Supported |
|---|---|
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning | Yes |
| Parallel tools | Yes |
| Image input | No |
| Roo Code ready | Yes |
How does GLM-5.3 Abliterated compare on cost?
Assumes 1,000 input + 300 output tokens per turn, repeated 1,000 times, at standard-tier rates without caching. Input / output shown per 1M tokens, rounded up to the cent.
Common questions about GLM-5.3 Abliterated
How much does the GLM-5.3 Abliterated API cost?
GLM-5.3 Abliterated costs $1.40 per 1M input tokens and $1.40 per 1M output tokens (cached input $0.40). Prices as of October 30, 2026.
What model ID and base URL do I use for GLM-5.3 Abliterated?
Use the model ID glm-5.3-abliterated with the base URL https://api.outrun.to/v1 and your Outrun API key. Route IDs: glm-5.3-abliterated-2 (Route 2).
Does GLM-5.3 Abliterated accept images?
No. GLM-5.3 Abliterated takes text input only.
Does Outrun store my prompts when I use GLM-5.3 Abliterated?
Outrun does not store your prompts, images or outputs unless you choose to save them.