Model Details
Where is GLM 4.7 Flash a perfect fit?
- Coding assistants and coding agents
- Software engineering and code generation
- High-volume agentic workloads
- Tool/function-calling applications
- Long-form text processing
- Chinese/English writing and translation
- Research and browsing agents
- Terminal-based coding agents
- Cost-sensitive reasoning workloads
- Self-hosted AI applications
- Subagents where a full-size frontier model would be excessive
Z.ai positions it as a lightweight deployment option that balances performance and efficiency, while its benchmark results show particularly strong performance for coding and agentic tasks.
Quick Model Estimate
Your GLM 4.7 Flash Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
Cost Breakdown
Prices are watched for changes and checked against the provider's own page.
Pricing
Benchmarks
Scores from standardized evaluations by Artificial Analysis and Design Arena. Higher is better — the indices summarize overall ability, while the detailed scores break down performance on individual benchmarks.
Artificial Analysis
Higher is better · benchmarked by Artificial AnalysisGraduate-level questions in biology, chemistry & physics
Expert-level questions across many academic domains
Precise following of detailed instructions
Tool-using agent tasks in a telecom support setting
Unpublished physics research reasoning problems
Long-context reasoning across large inputs
Complex command-line and terminal workflows
Breadth of factual knowledge across domains
How reliably the model avoids fabricated answers
| Variant | GPQA Diamond | Humanity's Last Exam | IFBench | τ²-Bench Telecom | AA-LCR | Terminal-Bench Hard | CritPt | Omniscience Accuracy | Omniscience Non-Hallucination |
|---|---|---|---|---|---|---|---|---|---|
| GLM-4.7-Flash (Reasoning) | 58.1% | 7.6% | 60.8% | 98.8% | 41.7% | 22% | 0.3% | 16.2% | 6.1% |
| GLM-4.7-Flash (Non-reasoning) | 45.2% | 5% | 46.3% | 91.8% | 20.3% | 3.8% | 0% | 13.1% | 5.7% |
Design Arena
Elo rating by arena & category| Variant | Arena | Category | Elo | Win % | Percentile | Avg time (ms) |
|---|---|---|---|---|---|---|
| glm-4.7-flash | models | 3d | 1,122 | 51.2% | 37 | 116,926 |
| glm-4.7-flash | models | codecategories | 1,180 | 53.1% | 53 | 150,068 |
| glm-4.7-flash | models | dataviz | 1,125 | 45.3% | 28 | 126,750 |
| glm-4.7-flash | models | gamedev | 1,139 | 49.7% | 39 | 153,698 |
| glm-4.7-flash | models | svg | 1,037 | 44.2% | 15 | 81,729 |
| glm-4.7-flash | models | uicomponent | 1,209 | 57.6% | 61 | 116,336 |
| glm-4.7-flash | models | website | 1,196 | 54% | 57 | 159,006 |
Compare GLM 4.7 Flash with
Two models side by side: worked costs, every rate, and every benchmark figure both of them report.
Other Models in the GLM 4.7 Family
FAQs about GLM 4.7 Flash
How much does GLM 4.7 Flash cost per 1M tokens?
GLM 4.7 Flash costs nothing for input tokens, and nothing for output tokens.
What does a typical workload cost with GLM 4.7 Flash?
1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs nothing with GLM 4.7 Flash at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use GLM 4.7 Flash?
GLM 4.7 Flash is available through Z.ai, free of charge for input tokens.
What is GLM 4.7 Flash's context window?
GLM 4.7 Flash has a context window of 200,000 tokens, and returns up to 131,072 tokens in a single response.
What input types does GLM 4.7 Flash support?
GLM 4.7 Flash accepts text input, and returns text.