GLM 5 Turbo API Pricing

GLM 5 Turbo by Zhipu costs $0.745 per million input tokens and $3.278 per million output tokens.

Price verified from Zhipu's pricing page.

Rates and limits

Input / 1M
$0.745
Output / 1M
$3.278
Cached input / 1M
$0.179
Batch discount
None
Context window
203K tokens
Released
January 2026

Pricing note: Sold on Zhipu BigModel (China), priced in CNY: ¥5 input / ¥22 output / ¥1.2 cache hit per 1M tokens for prompts under 32K; ¥7 / ¥26 / ¥1.8 at 32K and above (about $1.043 / $3.874 / $0.268). Cache storage is free for a limited time. Converted at 6.7110 CNY per USD (US Federal Reserve H.10, rate for 2026-09-25, released 2026-09-28). Not listed on the international Z.ai platform.

What GLM 5 Turbo costs per month

Token volume split 3:1 between input and output, with no prompt caching.

Tokens per monthInput / outputStandard
1M750K / 250K$1.38
10M7.5M / 2.5M$13.78
100M75M / 25M$137.83
Estimate your own workload with GLM 5 Turbo

Where to run GLM 5 Turbo

Prices above are Zhipu's direct rates. Cloud platforms can charge differently; the cloud platform view compares them.

GLM 5 Turbo pricing FAQ

How much does GLM 5 Turbo cost per million tokens?

GLM 5 Turbo costs $0.745 per million input tokens and $3.278 per million output tokens, as listed on Zhipu's pricing page on September 30, 2026.

How much does GLM 5 Turbo cost for 10 million tokens a month?

About $13.78 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching.

What is the context window of GLM 5 Turbo?

GLM 5 Turbo accepts up to 202,752 tokens of context.

Does GLM 5 Turbo support prompt caching?

Yes. Cached input tokens cost $0.179 per million, 76% less than the standard input rate.

Is there a batch discount for GLM 5 Turbo?

No batch API price is listed for GLM 5 Turbo.

Where can I use the GLM 5 Turbo API?

GLM 5 Turbo is available through Zhipu Open Platform and OpenRouter.

Compare with other models

Prices shown as input / output per million tokens. All model prices · Side-by-side comparison