Listings
All listings for GLM 4.5 Air
Every priced listing we track for this model. Back to GLM 4.5 Air
| Provider | Max Input Tokens | Input $/1M | Output $/1M | $/request | Tok/s | Latency |
|---|---|---|---|---|---|---|
Run by the model's maker Data from Zhipu BigModel Open Platform Pricing | 128K | CN¥0.80cache read CN¥0.16≈ $0.1195 USD (compared by USD value) | CN¥2.00≈ $0.2988 USD (compared by USD value) | — | — | — |
Run by the model's maker policy notesis processed in real-time to provide the Customer and End Users with the API Service and is not saved on our servers. — Z.ai privacy policy
Source: Z.ai privacy policy Data from Z.AI Pricing Fields by sourceFrom GenAI Prices: offering name, context length, unitFrom LiteLLM: max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, max input tokens, max output tokensFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image input, cache-write price | 128K | $0.20cache read $0.03 | $1.10 | — | — | — |
Data from 302.ai | 128K | $0.114 | $0.286 | — | — | — |
undercut?Suspiciously low input price: $0.014/1M against the official $0.1196/1M. We leave it out of the cheapest prices. Data from AIHubMix | —Not published by the provider | $0.014 | $0.084 | — | — | — |
Data from AIHubMix | 131K | $0.14 | $0.84 | — | — | — |
Data from FlowDot | 131K | $0.00 | $0.00 | — | — | — |
Data from FlowDot | 131K | $0.13 | $0.85 | — | — | — |
Data from Models.dev | 131K | $0.13 | $0.85 | — | — | — |
Data from Hugging Face Inference Providers Fields by sourceFrom GenAI Prices: offering name | 131K | $0.13 | $0.85 | — | — | — |
Data from GenAI Prices | 131K | $0.20 | $1.20 | — | — | — |
Data from GenAI Prices | 131K | $0.20 | $1.10 | — | — | — |
Data from Kilo AI Gateway Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input | 131K | $0.13cache read $0.025 | $0.85 | — | — | — |
Data from LLMGateway | 128K | $0.20cache read $0.03 | $1.10 | — | — | — |
Data from LLMGateway | —Not published by the provider | $0.20cache read $0.03 | $1.10 | — | — | — |
Data from NanoGPT Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 128K | $0.13cache read $0.025 | $0.85 | — | — | — |
Data from NanoGPT Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 128K | $0.13cache read $0.025 | $0.85 | — | — | — |
zero retention, per NanoGPTData privacy: zero data retention · prompts not retained · no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: License permits distillation — NanoGPT privacy policy Data from NanoGPT | —Not published by the provider | $0.1365cache read $0.0263 | $0.8925 | — | — | — |
zero retention, per NanoGPTData privacy: zero data retention · prompts not retained · no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: License permits distillation — NanoGPT privacy policy Data from NanoGPT | —Not published by the provider | $0.1365cache read $0.0263 | $0.8925 | — | — | — |
retention training unknown, per NanoGPTData privacy: retention_training_unknown
Source: NanoGPT policy notesprivacy: retention_training_unknown; distillation: License permits distillation — NanoGPT privacy policy Data from NanoGPT | —Not published by the provider | $0.147 | $0.903 | — | 73.2 | 2,527ms |
retention training unknown, per NanoGPTData privacy: retention_training_unknown
Source: NanoGPT policy notesprivacy: retention_training_unknown; distillation: License permits distillation — NanoGPT privacy policy Data from NanoGPT | —Not published by the provider | $0.147 | $0.903 | — | 73.2 | 2,527ms |
zero retention, per NanoGPTData privacy: zero data retention · prompts not retained · no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy Data from NanoGPT | —Not published by the provider | $0.21cache read $0.0315 | $1.155 | — | — | 705ms |
zero retention, per NanoGPTData privacy: zero data retention · prompts not retained · no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy Data from NanoGPT | —Not published by the provider | $0.21cache read $0.0315 | $1.155 | — | 79.8 | 6,376ms |
Data from Nous Portal Inference Gateway | 131K | $0.13cache read $0.025 | $0.85 | — | — | — |
Data from Helicone Costs | —Not published by the provider | $0.00 | $0.00 | — | — | — |
Data from OpenRouter | 131K | $0.13cache read $0.025 | $0.85 | — | 74 | 931ms |
Data from OpenRouter Fields by sourceFrom GenAI Prices: offering nameFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input | 131K | $0.13cache read $0.025 | $0.85 | — | — | — |
Data from OpenRouter | 131K | $0.14 | $0.86 | — | 48 | 1,054.5ms |
Data from OpenRouter | 131K | $0.20cache read $0.03 | $1.10 | — | 70 | 716.5ms |
Data from Requesty | 131K | $0.20 | $1.10 | — | — | — |
policy notesAI Gateway uses zero data retention by default — Vercel AI Gateway security & compliance documentation
It permanently deletes your prompts and responses after requests complete. — Vercel AI Gateway security & compliance documentation
requests only route to providers with verified ZDR agreements — Vercel AI Gateway security & compliance documentation
The provider allowlist lets team owners restrict which AI providers can serve requests through AI Gateway — Vercel AI Gateway security & compliance documentation
Vercel may store, process and transmit your information outside of your country of residence, which may have different data protection laws and may not offer the same level of protection or guarantees as in your country or the country where you initially provided the information. — Vercel privacy policy
Sources: Vercel AI Gateway security & compliance documentation, Vercel privacy policy Data from Vercel AI Gateway Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports function calling, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 128K | $0.20cache read $0.03 | $1.10 | — | — | — |
Data from ZenMux Fields by sourceFrom Models.dev: max completion tokens, supports function calling, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 128K | $0.1165cache read $0.0233 | $0.2911 | $0.01 | — | — |
Data from LiteLLM | 131K | $0.22 | $0.88 | — | — | — |
Data from flex.ai API | 131K | $0.14 | $0.86 | — | — | — |
Data from flex.ai Pricing | 128K | $0.14cache read $0.021 | $0.86 | — | — | — |
Data from LiteLLM | 131K | $0.20 | $1.10 | — | — | — |
Data from Models.dev | 131K | $0.20cache read $0.03 | $1.10 | — | — | — |
Data from IO Intelligence (io.net) | 131K | $0.1567cache read $0.0783 | $0.9367 | — | 0 | 487ms |
Data from Models.dev | 128K | $0.20cache read $0.03 | $1.10 | — | — | — |
Data from Models.dev | 128K | $0.20cache read $0.03 | $1.10 | — | — | — |
Data from Novita AI Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports function calling, supports parallel function calling, supports tool choice, supports system messages, supports prompt caching, supports reasoning, max input tokens, max output tokens, cache-read priceFrom Models.dev: max completion tokens, supports vision, supports image input | 131K | $0.13cache read $0.025 | $0.85 | — | — | — |
Data from Models.dev | 131K | $0.20cache read $0.03 | $1.10 | — | — | — |
Data from LiteLLM | 128K | $0.125 | $0.45 | — | — | — |
Data from PPIO | 131K | CN¥1.20cache read CN¥0.24≈ $0.1793 USD (compared by USD value) | CN¥2.00≈ $0.2988 USD (compared by USD value) | — | — | — |
Data from Qiniu AI Fields by sourceFrom Qiniu AI Model Plaza Pricing: supported input modalities, supported output modalities, rate limits, currency, unit, last updated, input tokens, output tokens | —Not published by the provider | CN¥0.00≈ $0.00 USD (compared by USD value) | CN¥0.00≈ $0.00 USD (compared by USD value) | — | — | — |
Data from SiliconFlow Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, input tokens, output tokens, currency, currency basis, last updated | 131K | $0.14 | $0.86 | — | — | — |
Data from Models.dev | 131K | $0.1495 | $0.8967 | — | — | — |
Data from Models.dev | 131K | $0.10 | $0.50 | — | — | — |
Data from Together AI Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, max input tokens, max output tokens | 131K | $0.20 | $1.10 | — | — | — |
Data from LiteLLM | 128K | $0.20 | $1.10 | — | — | — |
5 listings without a price are hidden.
Select any dotted value, label or icon to see where it comes from and how it is measured. How this data works