GLM-4.5-Air: Price, Context, Benchmarks, and Release Details
45.3
SI Score (method si-v3-retained-evidence-2)
37% confidence 37 percent, Low confidence — 2 of 7 expected sources in
Coverage 30% of expected source weight · 100% confidence at 80% coverage
Pillar breakdown
Coding (weight 40 percent) 20.5
Math (weight 15 percent) —
Preference (weight 15 percent) 71.5
Reasoning (weight 30 percent) —
Pillar weights: reasoning 30% · math 15% · coding 40% · preference 15%. Benchmark results use fixed 0–100 scales before averaging; incomplete evidence is shrunk toward 50.
Facts
- Input price / 1M
- $0.20Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Output price / 1M
- $1.10Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Context window
- 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Max output
- 98.3Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Released
- Jul 28, 2025models.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Open weights
- Yesmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - License
- not yet reported
- Input modalities
- textmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗
Benchmark results
2 results| Benchmark | Raw result | Normalized (0–100) | Pillar |
|---|---|---|---|
| lmarena text | 1383.8 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026
Retrieved Oct 9, 2026 · CC-BY-4.0 Open source ↗ | 71.5 | preference |
| terminal bench | 20.5%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published May 30, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription Open source ↗ | 20.5 | coding |
Normalization uses fixed absolute 0–100 scales for each unit, independently of other models that have a result on each benchmark. Coverage and evidence breadth still affect the composite; compare the evaluation conditions before reading a small score gap as decisive. “lab-reported” marks the provider's own published figure.
Sources: in and pending
in Reported (2)
- Official model cards via models.dev · arrived Oct 8, 2026
- LMArena / Arena · arrived Oct 8, 2026
pending Awaiting (5)
- ARC Prize · carries 13% of expected weight
- Epoch AI Benchmarking · carries 25% of expected weight
- Humanity’s Last Exam · carries 13% of expected weight
- LiveBench · carries 13% of expected weight
- Terminal-Bench · carries 6% of expected weight
The confidence % rises as pending sources publish. Some sources never cover some models — that is why 100% confidence arrives at 80% of expected weight, not at full coverage.