Pricingby GlyphGLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications.
Ways to buy 3
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
bf16 · cached $0.025 | $0.13 | $0.85 | $0.13 / $0.85Cheapest | $0.025 | Cheapest |
fp8 | $0.14 | $0.86 | $0.14 / $0.86+3% vs cheapest | n/a | +3% vs cheapest |
fp8 · cached $0.03 | $0.2 | $1.1 | $0.2 / $1.1+37% vs cheapest | $0.03 | +37% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $30.00 direct.
LiteLLM$30.00+0%
Vercel AI Gateway$30.00+0%
Requesty$31.50+5%
Eden AI$31.65+5.5%
OpenRouter$31.65+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Kong AI GatewayNot offeredNot offered
Neon AI GatewayNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Z.ai · 1M | $0.37 | $1.25 | $0.37 / $1.25 | $0.59 | 1M | Lab list price | · | GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. |
Z.ai · 1M | $2.8 | $8.8 | $2.8 / $8.8 | $4.3 | 1M | Lab list price | · | GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. |
Z.ai · 1M | $0.37 | $1.25 | $0.37 / $1.25 | $0.59 | 1M | Lab list price | · | GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. |
Z.ai · 1M | $0.012 | $0.158 | $0.012 / $0.158 | $0.049 | 1M | on Relace (fp4) | · | GLM-5.3-Flash is a native multimodal model from Z.ai. |
DeepSeek · 1MCheapest: $0.081 on Particle AI (us-flex) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.081 on Particle AI (us-flex) | · | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. |
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. |
 Titan Multimodal Embeddings G1Amazon Nova · 0K | $0.8 | Free | $0.8 / Free | $0.6 | 0K | Lab list price | · | Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. |
Cohere · 192K | $0.3 | $1.5 | $0.3 / $1.5 | $0.6 | 192K | Lab list price | · | Command A+ is Cohere's flagship model for enterprise agentic workflows. |
About GLM 4.5 Air
Takes text in and returns text. First listed Sep 23, 2026. Up to 98K output tokens. Blended price $0.31 per 1M tokens at 3 input to 1 output. Model id glm-4-5-air.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does GLM 4.5 Air cost?
$0.13 per million input tokens and $0.85 per million output tokens, with cached input at $0.025.
What is the context window of GLM 4.5 Air?
131K tokens, with up to 98K tokens of output.
Where is GLM 4.5 Air cheapest?
Of 3 routes tracked, Novita AI is cheapest at $0.13 input and $0.85 output per million tokens.