GLM-4.5 Air API Benchmarks, Pricing & Provider Data
Compare GLM-4.5 Air with another model
Choose a model to open its comparison page.
GLM-4.5 Air benchmark, API pricing, and provider data cover 112 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.
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 6 / 8
- Methodology
- V3.0
#1Math56.9Estimated2/4 Measured dimensions
#2Coding48.1Provisional1/4 Measured dimensions
#3Reasoning47RatedGlobal rank #513/4 Measured dimensions
#4Agents42.9Provisional1/4 Measured dimensions
#5Instruction following42.6Provisional1/4 Measured dimensions
#6Knowledge36Provisional1/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Aug 31, 2026Pricing
undefined metric} other undefined metrics}}
Input price$0.170/M#28 / 180Output price$0.980/M#45 / 180
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Score42.980% interval26.9–58.91/4 Measured dimensionsΤ²-bench results46.5#68 / 82
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Score48.180% interval34.2–62.01/4 Measured dimensionsLiveCodeBench68.4%#32 / 115SciCode30.6%#155 / 205
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score47#5180% interval38.4–55.73/4 Measured dimensionsMMLU-Pro81.5%#56 / 129GPQA73.3%#129 / 212
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score3680% interval20.0–52.11/4 Measured dimensionsArtificial Analysis Intelligence Index16.7#91 / 111AA-GPQA Diamond73.3#85 / 108
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Score56.980% interval45.0–68.72/4 Measured dimensionsAIME67.3%#23 / 68MATH-50096.5%#16 / 73
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
80% interval30.8–69.20/4 Measured dimensionsDesign Arena Website1158.0#57 / 75
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score42.680% interval26.6–58.61/4 Measured dimensionsAA-IFBench37.6#75 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
OpenRouter endpoints
3 endpointsThird-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 | 99.6% | — | — | undefined tokens / undefined tokens |
Z.AI z-ai/fp8 | $0.200/M | $1.10/M | 99.4% | — | — | undefined tokens / undefined tokens |
SiliconFlow siliconflow/fp8 | $0.140/M | $0.860/M | 0% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare GLM-4.5 Air API pricing across 110 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 100% | glm-4.5-air | default | $0.010/request | - | 29.5 t/s | 24.77 s | — | |
L1 100% | z-ai/glm-4.5-air:free | default | $0.010/request | - | 25.0 t/s | 53.96 s | — | |
L1 100% | glm-4.5-air | default | -68%$0.055/M | -58%$0.411/M | — | — | — | |
L1 100% | glm-4.5-air | sale | $0.400/M | $1.00/M | — | — | — | |
L1 100% | glm-4.5-air | default | -36%$0.110/M | -16%$0.822/M | — | — | — | |
L1 100% | glm-4.5-air | default | -52%$0.082/M | -44%$0.548/M | — | — | — | |
兔子API Free | L1 100% | glm-4.5-air | default | Free | Free | — | — | — |
L1 100% | glm-4.5-air | default | -72%$0.048/M Cache read$0.0072/M | -73%$0.264/M | — | — | — | |
L1 100% | z-ai/glm-4.5-air:free | default | $0.0050/request | - | — | — | — | |
L1 100% | glm-4.5-air | default | -68%$0.055/M | -58%$0.411/M | — | — | — | |
L1 99% | glm-4.5-air | other | -51%$0.083/M Cache read$0.012/M | -53%$0.458/M | — | — | — | |
L1 100% | glm-4.5-air | default | -3%$0.164/M | $1.10/M | — | — | — | |
L1 100% | glm-4.5-air | default | -92%$0.014/M Cache read$0.0021/M | -92%$0.075/M | — | — | — | |
L1 99% | glm-4.5-air | default | -48%$0.088/M | -33%$0.658/M | — | — | — | |
L1 100% | glm-4.5-air | default | $0.900/M | $6.00/M | — | — | — | |
L1 100% L2 0% | glm-4.5-air | default | $0.800/M Cache read$0.160/M | $6.00/M | — | — | — | |
L1 98% | zai-org/GLM-4.5-Air | default | -42%$0.098/M | -45%$0.538/M | — | — | — | |
L1 98% | glm-4.5-air-nothinking | default | $0.587/M | $3.92/M | — | — | — | |
L1 98% | glm-4.5-air | default | $0.587/M Cache read$0.117/M | $3.92/M | — | — | — | |
L1 100% | glm-4.5-air | default | $0.800/M | $1.20/M | — | — | — |
Alternatives & Similar Models
GLM-4.7
glm-4-7
Zhipu GLM-4.7 is a flagship GLM release from Zhipu AI with advanced Chinese-English reasoning, coding, and agent features.
GLM-5
glm-5
Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.
DeepSeek V3.2
deepseek-v3-2
DeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.
GLM-5.1
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
Frequently Asked Questions
- What benchmark data does GLM-4.5 Air include?
- LMSpeed shows GLM-4.5 Air benchmark context, API price, output speed, first-token latency, and provider data across 112 providers when those signals are available.
- What is the GLM-4.5 Air API price?
- GLM-4.5 Air has pricing from 112 providers, ranging from $0.0050/request to $75.00/M. OpenRouter Fans has the lowest listed price.
- What does the GLM-4.5 Air API pricing table include?
- The GLM-4.5 Air API pricing table compares 112 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest GLM-4.5 Air API pricing?
- OpenRouter Fans currently has the lowest listed GLM-4.5 Air price at $0.0050/request across 112 providers.
- Can I compare GLM-4.5 Air API price and speed together?
- Yes. LMSpeed shows GLM-4.5 Air API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is GLM-4.5 Air API free?
- Yes, GLM-4.5 Air free API options are available through 2 providerundefined other undefined} on LMSpeed, including Zero API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get GLM-4.5 Air free API access?
- LMSpeed currently lists 2 free API providerundefined other undefined} for GLM-4.5 Air: Zero API, 兔子API. Check each provider row before using it because free tier limits can change.