Back to models
available

Z.ai: GLM 5

z-ai/glm-5

Prices

Input

$1.00 per 1M tokens

low
Input (>32k ctx)

$0.8964 per 1M tokens

low
Input (cache write, >32k ctx)

$0.00 per 1M tokens

low
Input (cache write)

$0.00 per 1M tokens

medium
Input (cached read, >32k ctx)

$0.2241 per 1M tokens

low
Input (cached read)

$0.20 per 1M tokens

low
Output

$3.20 per 1M tokens

low
Output (>32k ctx)

$3.29 per 1M tokens

low

Also available on

The same model, sold by someone else. The price above is the maker's own.

54 sales channels for this model.
ChannelWhatPrice
Google Vertex AIInput$1.00 per 1M tokens
Input (cached read)$0.10 per 1M tokens
Output$3.20 per 1M tokens
Amazon BedrockInput$1.00 per 1M tokens
Input (batch)$0.50 per 1M tokens
Input (batch) (region: us-east-1)$0.50 per 1M tokens
Input (batch) (region: us-west-2)$0.50 per 1M tokens
Input (flex)$0.50 per 1M tokens
Input (flex) (region: us-east-1)$0.50 per 1M tokens
Input (flex) (region: us-west-2)$0.50 per 1M tokens
Input (priority)$1.75 per 1M tokens
Input (priority) (region: us-east-1)$1.75 per 1M tokens
Input (priority) (region: us-west-2)$1.75 per 1M tokens
Input (region: us-east-1)$1.00 per 1M tokens
Input (region: us-west-2)$1.00 per 1M tokens
Output$3.20 per 1M tokens
Output (batch)$1.60 per 1M tokens
Output (batch) (region: us-east-1)$1.60 per 1M tokens
Output (batch) (region: us-west-2)$1.60 per 1M tokens
Output (flex)$1.60 per 1M tokens
Output (flex) (region: us-east-1)$1.60 per 1M tokens
Output (flex) (region: us-west-2)$1.60 per 1M tokens
Output (priority)$5.60 per 1M tokens
Output (priority) (region: us-east-1)$5.60 per 1M tokens
Output (priority) (region: us-west-2)$5.60 per 1M tokens
Output (region: us-east-1)$3.20 per 1M tokens
Output (region: us-west-2)$3.20 per 1M tokens
Microsoft Azure · azure-aiInput$1.10 per 1M tokens
Input (cached read)$0.22 per 1M tokens
Output$3.52 per 1M tokens
Alibaba Model StudioInput$0.573 per 1M tokens
Output$2.58 per 1M tokens
Alibaba Model Studio · alibaba-cnInput$0.573 per 1M tokens
Input (>32k ctx)$0.86 per 1M tokens
Output$2.58 per 1M tokens
Output (>32k ctx)$3.15 per 1M tokens
OpenRouterInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
OpenRouter · z-aiInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Coding plan · alibaba-coding-planInput$0.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$0.00 per 1M tokens
Coding plan · alibaba-coding-plan-cnInput$0.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$0.00 per 1M tokens
Coding plan · tencent-coding-planInput$0.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$0.00 per 1M tokens
Token plan · alibaba-token-planInput$0.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$0.00 per 1M tokens
Token plan · alibaba-token-plan-cnInput$0.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$0.00 per 1M tokens
Other · 302aiInput$0.60 per 1M tokens
Input (>32k ctx)$0.90 per 1M tokens
Output$2.60 per 1M tokens
Output (>32k ctx)$3.20 per 1M tokens
Other · abacusInput$1.00 per 1M tokens
Output$3.20 per 1M tokens
Other · basetenInput$0.95 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.15 per 1M tokens
Other · commandcodeInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · crossmodelInput$0.60 per 1M tokens
Input (>32k ctx)$0.80 per 1M tokens
Input (cache write, >32k ctx)$0.80 per 1M tokens
Input (cache write)$0.60 per 1M tokens
Input (cached read, >32k ctx)$0.20 per 1M tokens
Input (cached read)$0.16 per 1M tokens
Output$3.00 per 1M tokens
Output (>32k ctx)$3.40 per 1M tokens
Other · deepinfraInput$0.60 per 1M tokens
Input (cached read)$0.12 per 1M tokens
Output$2.08 per 1M tokens
Other · digitaloceanInput$1.00 per 1M tokens
Input (>32k ctx)$0.86 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Output (>32k ctx)$3.15 per 1M tokens
Other · dinferenceInput$0.75 per 1M tokens
Output$2.40 per 1M tokens
Other · edenaiInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · fastrouterInput$0.60 per 1M tokens
Input (cached read)$0.12 per 1M tokens
Output$2.08 per 1M tokens
Other · huggingfaceInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · huggingface-novitaInput$1.00 per 1M tokens
Output$3.20 per 1M tokens
Other · huggingface-togetherInput$1.00 per 1M tokens
Output$3.20 per 1M tokens
Other · impossiblInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · kiloInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · llmgatewayInput$0.573 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.144 per 1M tokens
Output$2.58 per 1M tokens
Other · llmgateway-providersInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Input (cached read) (host: embercloud)$0.144 per 1M tokens
Input (cached read) (host: novita)$0.20 per 1M tokens
Input (host: embercloud)$0.72 per 1M tokens
Input (host: novita)$1.00 per 1M tokens
Output$3.20 per 1M tokens
Output (host: embercloud)$2.30 per 1M tokens
Output (host: novita)$3.20 per 1M tokens
Other · meganovaInput$0.80 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$2.56 per 1M tokens
Other · meliousInput$1.10 per 1M tokens
Input (cached read)$0.2666 per 1M tokens
Output$3.36 per 1M tokens
Other · merge-gatewayInput$1.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · mistralInput$1.40 per 1M tokens
Input (cached read)$0.14 per 1M tokens
Output$4.40 per 1M tokens
Other · nano-gptInput$0.60 per 1M tokens
Input (cached read)$0.10 per 1M tokens
Output$1.90 per 1M tokens
Other · novitaInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · novita-aiInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · ofoxInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · opencodeInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · openrouterInput$0.60 per 1M tokens
Input (cached read)$0.12 per 1M tokens
Output$1.92 per 1M tokens
Other · orcarouterInput$1.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.26 per 1M tokens
Output$3.20 per 1M tokens
Other · poeInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · qiniu-aiInput$0.5797 per 1M tokens
Input (>32k ctx)$0.8696 per 1M tokens
Output$2.61 per 1M tokens
Output (>32k ctx)$3.19 per 1M tokens
Other · scnetInput$0.00 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$0.00 per 1M tokens
Other · siliconflowInput$0.95 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$2.55 per 1M tokens
Other · siliconflow-cnInput$1.00 per 1M tokens
Output$3.20 per 1M tokens
Other · streamlakeInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · temprInput$1.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · tensorxInput$1.00 per 1M tokens
Input (cache write)$1.25 per 1M tokens
Input (cached read)$0.25 per 1M tokens
Output$3.20 per 1M tokens
Other · together-aiInput$1.00 per 1M tokens
Output$3.20 per 1M tokens
Other · togetheraiInput$1.00 per 1M tokens
Output$3.20 per 1M tokens
Other · tokengoInput$0.89 per 1M tokens
Input (cached read)$0.2226 per 1M tokens
Output$3.26 per 1M tokens
Other · veniceInput$1.00 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.20 per 1M tokens
Other · vercelInput$1.00 per 1M tokens
Output$3.20 per 1M tokens
Other · zenmuxInput$0.58 per 1M tokens
Input (>32k ctx)$0.87 per 1M tokens
Input (cached read, >32k ctx)$0.22 per 1M tokens
Input (cached read)$0.14 per 1M tokens
Output$2.60 per 1M tokens
Output (>32k ctx)$3.18 per 1M tokens

Specifications

Provider
z-ai
Context window
204,800
Max output tokens
202,752
Open weights
yes
Released
02/12/2026
Retires
no date announced
First seen by this tracker

Price history

Input — per 1M tokens

1009/14/2026today
Recorded changes for Input
FromAmount
09/14/20260.552
09/14/20261
10/22/20260.5976
10/23/20261
10/25/20260.5976
10/29/20261
11/01/20260.5976
11/03/20261
11/05/20260.5976
11/08/20261
11/09/20260.5976
11/11/20261
11/13/20260.5976
11/15/20261

Input (cached read) — per 1M tokens

0.2009/14/2026today
Recorded changes for Input (cached read)
FromAmount
09/14/20260.138
09/14/20260.2
10/22/20260.1494
10/23/20260.2
10/25/20260.1494
10/29/20260.2
11/01/20260.1494
11/03/20260.2
11/05/20260.1494
11/08/20260.2
11/09/20260.1494
11/11/20260.2
11/13/20260.1494
11/15/20260.2

Output — per 1M tokens

3.2009/14/2026today
Recorded changes for Output
FromAmount
09/14/20262.48
09/14/20263.2
10/22/20262.69
10/23/20263.2
10/25/20262.69
10/29/20263.2
11/01/20262.69
11/03/20263.2
11/05/20262.69
11/08/20263.2
11/09/20262.69
11/11/20263.2
11/13/20262.69
11/15/20263.2

No changes recorded

Input (cache write)
0 per 1M tokens, unchanged since 09/14/2026
Input (>32k ctx)
0.8964 per 1M tokens, unchanged since 10/21/2026
Output (>32k ctx)
3.29 per 1M tokens, unchanged since 10/21/2026
Input (cached read, >32k ctx)
0.2241 per 1M tokens, unchanged since 10/21/2026
Input (cache write, >32k ctx)
0 per 1M tokens, unchanged since 10/21/2026

Last updated 11/16/2026, 01:12