GLM 5.3
z-ai/glm-5.3GLM-5.3 is Z.ai's flagship text model for complex software engineering and long-horizon agent work, built on the same base model as GLM-5.2 with all gains coming from expanded post-training. Z.ai highlights stronger agentic coding, terminal operation, and vulnerability discovery and exploitation analysis for security work. It always runs with reasoning enabled at selectable effort levels and accepts text only; choose GLM-5.3-Flash for image input or lighter, faster serving.
- Input price
- $1.05
$1.40USD / 1M tokens - Output price
- $3.30
$4.40USD / 1M tokens - Context window
- 1M
- Max output
- 131.1K
Try the model
Playground
Try a prompt
Your response will appear here
Choose an example or write a prompt, then click Run.
Model card
Specifications
Pricing
- Input
- $1.05 / 1M tokens
- Output
- $3.30 / 1M tokens
- Cache read
- $0.19 / 1M tokens
Context & modalities
- Context window
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Input
- Text
- Output
- Text
Capabilities
- Chat
- Supported
- Vision
- Not supported
- Reasoning
- Supported
- Structured output
- Supported
- Function calling
- Supported
- Audio input
- Not supported
Access
- Provider
- Z.ai
- Model ID
- z-ai/glm-5.3
- Execution
- sync
- Base URL
- https://api.sandbase.ai
- API
- Chat Completions API
- Endpoint
- /v1/chat/completions
Independent evaluations
Benchmarks
Scores on standardized evaluations, compared with other models on SandBase.
Metrics sourced from Artificial Analysis · Intelligence Index v4.3
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/chat/completions" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "z-ai/glm-5.3",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"Choose your model
Compare models
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
GLM 5.3This model Z.ai | 1M | $1.05 | $3.30 | Aug 18, 2026 |
Z.ai | — | Coming soon | Coming soon | Coming soon |
Z.ai | 1M | $0.37 | $1.25 | Sep 18, 2026 |
Z.ai | 1M | $0.15 | $0.50 | Aug 26, 2026 |
Z.ai | 1M | $1.40 | $4.40 | Jun 16, 2026 |
Z.ai | 128K | $0.20 | $1.10 | Jul 25, 2025 |
Questions
FAQ
How do I call Z.ai GLM 5.3 through SandBase?
Create a SandBase API key, then send requests with the model ID "z-ai/glm-5.3" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.
How much does Z.ai GLM 5.3 cost?
$1.05 per 1M input tokens and $3.30 per 1M output tokens with the current 25% discount (list price $1.40 / $4.40), billed per request from your SandBase balance.
What is the context window of Z.ai GLM 5.3?
1M tokens of context, with up to 131.1K output tokens per response.
How does Z.ai GLM 5.3 score on benchmarks?
Z.ai GLM 5.3 scores 44.8 on the Artificial Analysis Intelligence Index (v4.3), ranking #13 of 84 models on SandBase; Coding Index 74.8, Agentic Index 53.1. Source: Artificial Analysis, measured as GLM-5.3 (Max).
Which features does Z.ai GLM 5.3 support?
Z.ai GLM 5.3 supports reasoning, function calling, structured output. See Specifications above for the full list.
Do I need a separate Z.ai account?
No. One SandBase API key and balance gives you access to Z.ai GLM 5.3 and the other models in the catalog; you do not need to sign up with Z.ai separately.