GLM 4.5 Air

Provider: Zhipu AI (GLM) CN Official API price

Input price
$0.20
/ 1M tokens
Output price
$1.10
/ 1M tokens
Cache price
$0.03
/ 1M tokens (read)
Context
131K tokens
Max output 98K tokens

Overview

Zhipu AI's GLM 4.5 Air is a lightweight MoE flagship variant built for agent workloads. It supports a 131k context window and a 98k max output.

Strengths

  • Input cost of $0.20 per million tokens
  • Cached input drops to $0.03 per million tokens
  • Supports native function-calling and thinking capabilities
  • Knowledge cutoff extends to December 2024

Best use cases

  • Running high-frequency agent tool-use loops
  • Processing long documents under 131k tokens
  • Cost-sensitive reasoning and extraction pipelines

Pricing position

Input matches Qwen3 VL 30B and Saba at $0.20/M, but output at $1.10/M sits higher than DeepSeek V4.1 Flash ($0.78/M).

Caveats

Context window of 131k is smaller than Flash-tier alternatives reaching 1M tokens.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
98K tokens
Knowledge cutoff
2024-12-31
Listed on OpenRouter
2025-07-25
Tracked since
2026-05-09
Last updated
2026-11-10

Features

Function callingReasoning

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.08
1M (small app) 1 0.5 $0.75
10M (mid scale) 10 5 $7.50
100M (large) 100 50 $75.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Zhipu AI (GLM)

Similar-priced models

Source: OpenRouter API (z-ai/glm-4.5-air)