← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
GLM 4.5 Air Pricing
Z.ai · z-ai-glm-4-5-air
Input / 1M tokens
$0.130
Output / 1M tokens
$0.850
Context window
131,072 tokens
≈ 175 pages of text
Max output
98,304 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0005
1,000 requests / month$0.496/mo10,000 requests / month$4.96/mo100,000 requests / month$49.60/moEstimate your own workloadOpens the calculator with GLM 4.5 Air preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jun 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Handles large context windows efficiently for document summarization and long-form generation at low per-token cost.
The business tradeoff
Reasoning depth and instruction following lag behind closed flagship models; output quality varies with local or third-party inference setups.
Cheaper from Z.ai
Head-to-head
Vendor list rates, as of Jun 16, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.