GLM-4.7
DeprecatedGLM-4.7 is Zhipu AI's language model with a 205K context window and up to 131K output tokens, available from 13 providers, starting at $0.4 / 1M input and $1.75 / 1M output. A multilingual MoE LLM from Z AI designed for complex reasoning, agentic coding, and tool use, building on the GLM-4.6 architecture.
| Benchmarks | |
|---|---|
| Intelligence Index | #99 |
| Coding Index | #76 |
| Math Index | #11 |
| MMLU-Pro | #27 |
| GPQA | #82 |
| HLE | #88 |
| LiveCodeBench | #7 |
| IFBench | #80 |
| Time to First Token | #406 |
| SciCode | #71 |
| AIME 2025 | #11 |
| LCR | #122 |
| TerminalBench Hard | #94 |
| TAU2 | #20 |
| Output TPS | #150 |
Capabilities
Input3/5
Text✓
Image✓
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities7/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill✓
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Flex | Fast | Batch | |||||
|---|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.431 | $2.01 | N/A | — | — | — | — | $0.215 | $1.00 | |
| $0.6 | $2.20 | N/A | $0.3 | $1.10 | $1.05 | $3.85 | $0.3 | $1.10 | |
| $0.6 | $2.20 | N/A | — | — | — | — | — | — | |
| $2.25 | $2.75 | N/A | — | — | — | — | — | — | |
| $0.4 | $1.75 | $0.08 | — | — | — | — | — | — | |
| $0.6 | $2.20 | $0.3 | — | — | — | — | — | — | |
| $0.6 | $2.20 | $0.06 | — | — | — | — | — | — | |
| $0.6 | $2.20 | N/A | — | — | — | — | — | — | |
| $0.6 | $2.20 | $0.11 | — | — | — | — | — | — | |
| $0.4 | $1.75 | $0.08 | — | — | — | — | — | — | |
| $0.45 | $2.00 | N/A | — | — | — | — | — | — | |
| $0.6 | $2.20 | $0.12 | — | — | — | — | — | — | |
| $0.6 | $2.20 | $0.11 | — | — | — | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host GLM-4.7, ranked by cheapest on-demand price. The model needs about 860 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 | |
|---|---|---|---|---|---|---|
| Standard_ND96is_MI300X_v5 |  Azure | 8× AMD Instinct MI300X GPU (192GB) | 1536 GB | $48.00/hr | ||
| Standard_ND96isr_MI300X_v5 | Azure | 8× AMD Instinct MI300X | 1536 GB | $48.00/hr | ||
| p5en.48xlarge |  AWS | 8× H200 | 1128 GB | $63.30/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| GLM-4.7 | 205K | $0.400 | $1.75 | Current | |
| GLM-4.6 | 205K | $0.430 | $1.75 | Deprecated | |
| GLM-4.5 | 131K | $0.400 | $1.60 | Deprecated | |
| GLM-4.5 Air | 131K | $0.125 | $0.450 | Available |