GLM 5.3 Uncensored API
Model ID: glm-5.3-uncensored · Developer: Zhipu AI · Available on 7API: yes, as of 2026-11-20
An uncensored GLM-5.3 at the same per-token rate as the standard model, with the full 1M-token context window. A strong default for uncensored agents and coding.
GLM 5.3 Uncensored is an uncensored version of GLM 5.3, available through 7API's uncensored AI API. Call GLM 5.3 Uncensored with any OpenAI- or Anthropic-compatible client. Use base URL https://7api.st/v1 (OpenAI) or https://7api.st (Anthropic) and send "model": "glm-5.3-uncensored".
Specifications
| Model ID | glm-5.3-uncensored |
| Context window | 1,000,000 tokens |
| Max output | 65,536 tokens |
| Input | Text |
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning effort | low, high, xhigh, max (default high) |
| API formats | Chat Completions, Responses, Anthropic Messages |
Pricing
| USD per 1M tokens | |
|---|---|
| Input | $0.05 |
| Output | $0.05 |
| Cached input | $0.01 |
For example, an agent turn with 150,000 cached input tokens, 2,000 new input tokens and 800 output tokens costs about $0.0016 on GLM 5.3 Uncensored. Billing is pay per token from a prepaid balance. See Pricing and billing.
Benchmarks
Independent leaderboards don't test uncensored builds. The base model, GLM 5.3, scores 45 on the Artificial Analysis Intelligence Index at max effort. Expect GLM 5.3 Uncensored to be close to that on general tasks, and test it on your own prompts.
GLM 5.3 Uncensored vs. other GLM models
| Model | Type | Based on | Input / 1M | Output / 1M | Cached / 1M | Max output | Reasoning effort |
|---|---|---|---|---|---|---|---|
| GLM 5.3 | Standard | — | $0.05 | $0.05 | $0.01 | 66K | low high xhigh max |
| GLM 5.3 Uncensored | Uncensored | GLM 5.3 | $0.05 | $0.05 | $0.01 | 66K | low high xhigh max |
| GLM 5.3 Flash Uncensored | Uncensored | GLM 5.3 Flash | $0.025 | $0.025 | $0.0025 | 66K | low high xhigh max |
| GLM 5.3 Abliterated | Abliterated | GLM 5.3 | $0.80 | $0.80 | $0.25 | 130K | high xhigh max |
Example
from openai import OpenAI
client = OpenAI(base_url="https://7api.st/v1", api_key="YOUR_7API_KEY")
r = client.chat.completions.create(
model="glm-5.3-uncensored",
messages=[{"role": "user", "content": "Write a haiku about caching."}],
)
print(r.choices[0].message.content)In Claude Code: /model claude-glm-5.3-uncensored. Setup guides: Claude Code, OpenCode, Codex, Cursor.
Related models
- GLM 5.3 Flash Uncensored: $0.025/M, $0.0025/M cached, 1M context
- GLM 5.3 Abliterated: $0.80/M, $0.25/M cached, 1M context
- GLM 5.2: $0.06/M, $0.017/M cached, 1M context
- GLM 5.3: $0.05/M, $0.01/M cached, 1M context
- GLM 5.3 Flash: $0.025/M, $0.0025/M cached, 1M context
- All uncensored and abliterated models
- What is abliterated AI?
How much does GLM 5.3 Uncensored cost?
The same per-token rate as standard GLM-5.3, shown in the pricing table above, with a lower rate for cached input.
GLM 5.3 Uncensored vs GLM 5.3 Abliterated?
GLM 5.3 Uncensored costs much less and suits volume and agent work. GLM 5.3 Abliterated has refusals removed at the weight level, refuses less often and allows longer outputs.
Also searched as: GLM 5.3 Uncensored, GLM-5.3 Uncensored, glm-5.3-uncensored, uncensored GLM.
