GLM-5.3
GLM-5.3 is Zhipu AI's language model with a 1.3M context window and up to 944K output tokens, available from 16 providers, starting at $1.13 / 1M input and $3.94 / 1M output. Z AI's flagship reasoning LLM sharing its base with GLM-5.2, with targeted improvements for complex software engineering and agentic tasks.
| Benchmarks | |
|---|---|
| Intelligence Index | #10 |
| Coding Index | #14 |
| GPQA | #26 |
| HLE | #24 |
| Time to First Token | #516 |
| SciCode | #5 |
| LCR | #41 |
| Output TPS | #170 |
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities8/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search✓
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill✓
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Fast | Batch | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Cache Write 5m $ / 1M | Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $1.13 | $3.94 | $0.282 | N/A | — | — | — | — | — | — | |
| $1.40 | $4.40 | N/A | N/A | — | — | — | $0.7 | $2.20 | N/A | |
| $1.40 | $4.40 | $0.14 | N/A | — | — | — | — | — | — | |
| $1.40 | $4.40 | $0.26 | $1.40 | — | — | — | — | — | — | |
| $1.40 | $4.40 | $0.26 | N/A | $1.75 | $5.50 | $0.325 | — | — | — | |
| $1.26 | $3.96 | $0.234 | N/A | — | — | — | — | — | — | |
| $1.40 | $4.40 | N/A | N/A | — | — | — | — | — | — | |
| $1.40 | $4.40 | $0.14 | N/A | — | — | — | $0.7 | $2.20 | N/A | |
| $1.40 | $4.40 | N/A | N/A | — | — | — | — | — | — | |
| $1.40 | $4.40 | $0.26 | N/A | — | — | — | — | — | — | |
| $1.40 | $4.40 | $0.26 | N/A | — | — | — | N/A | N/A | N/A | |
| — | — | — | — | — | — | — | $0.7 | $2.20 | $0.13 | |
| $1.40 | $4.40 | $0.26 | N/A | — | — | — | — | — | — | |
| $1.68 | $5.28 | N/A | N/A | — | — | — | $0.84 | $2.64 | N/A | |
| $1.40 | $4.40 | $0.26 | N/A | — | — | — | — | — | — | |
| $1.40 | $4.40 | $0.14 | N/A | N/A | N/A | N/A | — | — | — | |
| — | — | — | — | $2.10 | $6.60 | $0.21 | — | — | — | |
| $1.40 | $4.40 | $0.26 | N/A | — | — | — | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host GLM-5.3, ranked by cheapest on-demand price. The model needs about 1808 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region |
|---|---|---|---|---|---|
| p6-b300.48xlarge |  AWS | 8× B300 | 2149 GB | $142.42/hr |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| GLM-5.3 Flash | 1.3M | $0.090 | $0.300 | Available | |
| GLM-5.3 | 1.3M | $1.13 | $3.94 | Current | |
| GLM-5.3 (50% off) | 1.0M | — | — | Available | |
| GLM-5.2 Fast | 1.0M | $2.10 | $6.60 | Available | |
| GLM-5.2 | 1.0M | $0.610 | $1.98 | Available | |
| GLM-5V Turbo | 205K | $0.704 | $3.10 | Available | |
| GLM-5 Turbo | 203K | $1.20 | $4.00 | Available | |
| GLM-5.1 Non-Reasoning | — | — | — | — | Available |
| GLM-5 Non-Reasoning | — | — | — | — | Available |
| GLM-5 Code | — | 200K | $1.20 | $5.00 | Available |
| GLM-5.1 CC | — | 200K | $0.060 | $0.220 | Available |