Choose a model to open its comparison page.
GLM-4.5 Air benchmark, API pricing, and provider data cover 82 API providers, with prices starting at $0.0050/request. GLM-4.5 Air free API options are available from 2 providers. The page also shows measured API speed and first-token latency.
Zhipu AI GLM-4.5 Air is a lightweight GLM-4.5 variant optimized for low-latency Chinese and English dialogue, retrieval-augmented apps, and edge deployments.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
2 metrics
2 metrics
1 metric · Provisional
3 metrics · Estimated
4 metrics · Rated
5 metrics · Provisional
2 metrics · Estimated
0 metrics · Provisional
1 metric · Provisional
1 metric · Provisional
Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Novita novita/bf16 | $0.130/M | $0.850/M | 99.7% | — | — | 131.1K tokens / 98.3K tokens |
Z.AI z-ai/fp8 | $0.200/M | $1.10/M | 98.2% | — | — | 131.1K tokens / 98.3K tokens |
SiliconFlow siliconflow/fp8 | $0.140/M | $0.860/M | 97.4% | — | — | 131.1K tokens / 131.1K tokens |
Compare GLM-4.5 Air API pricing across 80 providers. Prices range from $0.0050/request to $75.00/M. OpenRouter Fans offers the lowest rate at $0.0050/request. 2 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 97% | glm-4.5-air | default | $0.010/request | - | 29.5 t/s | 24.77 s | — | |
L1 97% | z-ai/glm-4.5-air:free | default | $0.010/request | - | 25.0 t/s | 53.96 s | — | |
L1 100% | glm-4.5-air | sale | $0.400/M | $1.00/M | — | — | — | |
L1 100% | glm-4.5-air | default | -60%$0.068/M | -72%$0.274/M | — | — | — | |
L1 100% | glm-4.5-air | default | -92%$0.014/M Cache read$0.0021/M | -92%$0.075/M | — | — | — | |
L1 100% | glm-4.5-air | default | -25%$0.127/M | -48%$0.510/M | — | — | — | |
L1 100% | zai-org/GLM-4.5-Air | 5倍倍率分组 | -44%$0.096/M | -40%$0.589/M | — | — | — | |
L1 100% | glm-4.5-air | default | $0.010/request | - | — | — | — | |
L1 100% | zai-org/GLM-4.5-Air | default | -42%$0.098/M | -45%$0.538/M | — | — | — | |
L1 100% | glm-4.5-air-nothinking | default | $0.587/M | $3.92/M | — | — | — | |
L1 100% | glm-4.5-air | default | $0.587/M Cache read$0.117/M | $3.92/M | — | — | — | |
L1 100% | glm-4.5-air | default | -19%$0.137/M | -44%$0.548/M | — | — | — | |
L1 100% | glm-4.5-air | other | -51%$0.083/M Cache read$0.012/M | -53%$0.458/M | — | — | — | |
兔子API Free | L1 100% | glm-4.5-air | default | Free | Free | — | — | — |
L1 100% | z-ai/glm-4.5-air:free | default | $0.0050/request | - | — | — | — | |
L1 100% | glm-4.5-air | default | -60%$0.068/M | -72%$0.274/M | — | — | — | |
L1 100% | glm-4.5-air | default | -72%$0.048/M Cache read$0.0072/M | -73%$0.264/M | — | — | — | |
L1 100% | glm-4.5-air | default | -36%$0.110/M | -55%$0.438/M | — | — | — | |
L1 100% | glm-4.5-air | default | $0.219/M | -66%$0.329/M | — | — | — | |
L1 100% | glm-4.5-air | default | -25%$0.127/M | -48%$0.510/M | — | — | — |
