GLM-4.5-Air (glm-4.5-air) is a chat model from zai with a 128K-token context window; open-weight (106B parameters); capabilities tools, reasoning; input text; output text.
128KContext
32KMax output
$0.2$ / 1M in
16.5Intelligence
78.49tok / s
Pricing
Input
$0.2 / 1M tokens
Output
$1.1 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.
Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.
Benchmarks
Intelligence index
16.5
Math
80.7
Cited from a public third-party leaderboard — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-24.
Performance
Throughput
78.49 tokens/s
Latency (TTFT)
1.394 s
Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-22.