GLM 5.3
A 1M-context reasoning model built for complex coding and long-running agentic tasks.
Quantization
FP8
Open weights
Context Window
1.0M
Tokens
Intelligence
44.8
AA Index v4.3
Released
Aug 2026
25 Aug 2026
Frontier reasoning, open weights
GLM 5.3 is Z.ai's open-weight reasoning model for complex coding, long-horizon agentic work, tool use, cybersecurity analysis and repository-scale engineering.
It provides a 1M-token context window and configurable reasoning effort, so you can dial thinking budget up for hard planning problems and down for high-volume throughput — at a fraction of closed frontier pricing.
1M context · configurable reasoning effort
Best for repository-scale engineering
Complex Coding
Repository-scale engineering: multi-file edits, large refactors and iterative debugging across long sessions.
Agentic Workflows
Configurable reasoning effort for long-horizon planning, tool orchestration and recovery across many steps.
Cybersecurity Analysis
Reasoning over codebases, logs and configurations to surface vulnerabilities and explain exploit paths.
Long-Context Research
A 1M-token window keeps entire repositories, specs and document sets in a single request.
Also strong on research synthesis and enhanced structured generation.
Flexible Pricing Tiers
Choose the optimal balance of speed and cost for your workflow. Prices are per 1M tokens.
| Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| Batch | $0.70 | $2.20 |
| Async | $1.05 | $3.30 |
| Realtime | $1.40 | $4.40 |
Context window natively supported up to 1,048,576 tokens. We can offer custom pricing for bulk discounts, large workloads, and dedicated deployments — reach out to [email protected].
Start Building in Minutes
GLM 5.3 is accessible via OpenAI-compatible endpoints. Default sampling: temperature=1.0, top_p=0.95.
from openai import OpenAI
client = OpenAI(
api_key="your-api-key-here",
base_url="https://api.doubleword.ai/v1"
)
# Long-horizon agentic coding task
response = client.chat.completions.create(
model="zai-org/GLM-5.3",
messages=[
{"role": "user", "content": "Audit this repository for unsafe deserialization and open a patch plan."}
],
temperature=1.0,
top_p=0.95,
)
print(response.choices[0].message.content)💡 Pro Tip
Route long-running agent steps through the async tier and bulk evals through batch — same model, same API, at half the realtime rate. See the docs for the batch job format.