Z.AI

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by Z.AI

Model name

18 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
GLM 4.5 Air FP8 z-ai/GLM-4.5-Air:zai	131k	$0.21/M	$1.16/M	$0.03/M	N/A	1.7s	44 tps
GLM 4.5 Air (Thinking) FP8 z-ai/GLM-4.5-Air:thinking:zai	131k	$0.21/M	$1.16/M	$0.03/M	N/A	1.7s	44 tps
GLM 4.5V z-ai/glm-4.5v	64k	$0.60/M	$1.80/M	N/A	N/A	N/A	N/A
GLM 4.5V Thinking z-ai/glm-4.5v:thinking	64k	$0.60/M	$1.80/M	N/A	N/A	N/A	N/A
GLM 4.6 FP4 z-ai/glm-4.6:zai	203k	$0.63/M	$2.31/M	$0.12/M	N/A	9.3s	25 tps
GLM 4.6 (Thinking) FP4 z-ai/glm-4.6:thinking:zai	203k	$0.63/M	$2.31/M	$0.12/M	56.8%	9.3s	25 tps
GLM 4.6V Original z-ai/glm-4.6v-original	128k	$0.60/M	$0.90/M	N/A	N/A	N/A	N/A
GLM 4.7 FP4 z-ai/glm-4.7:zai	203k	$0.63/M	$2.31/M	$0.12/M	N/A	9.2s	24 tps
GLM 4.7 (Thinking) FP4 z-ai/glm-4.7:thinking:zai	203k	$0.63/M	$2.31/M	$0.12/M	39.9%	9.2s	24 tps
GLM 5 FP8 z-ai/glm-5:zai	203k	$1.05/M	$3.36/M	$0.21/M	0%	7s	51 tps
GLM 5 (Thinking) FP8 z-ai/glm-5:thinking:zai	203k	$1.05/M	$3.36/M	$0.21/M	0%	7s	51 tps
GLM 5.1 FP8 z-ai/glm-5.1:zai	203k	$1.47/M	$4.62/M	$0.27/M	43.2%	9.6s	23 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:zai	203k	$1.47/M	$4.62/M	$0.27/M	33.5%	9.6s	23 tps
GLM 5.2 FP8 z-ai/glm-5.2:zai	1.0M	$1.47/M	$4.62/M	$0.27/M	4.1%	2.4s	62 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:zai	1.0M	$1.47/M	$4.62/M	$0.27/M	4.1%	2.4s	62 tps
GLM 5.3 FP8 z-ai/glm-5.3:zai	1.0M	$1.47/M	$4.62/M	$0.27/M	72.1%	2.9s	53 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:zai	1.0M	$1.47/M	$4.62/M	$0.27/M	46.1%	2.9s	53 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:zai	1.0M	$0.16/M	$0.53/M	$0.03/M	91.5%	3.9s	31 tps

GLM 4.5 Air

FP8

z-ai/GLM-4.5-Air:zai

Context

131k

Input /M

$0.21/M

Output /M

$1.16/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

1.7s

Throughput

44 tps

GLM 4.5 Air (Thinking)

FP8

z-ai/GLM-4.5-Air:thinking:zai

Context

131k

Input /M

$0.21/M

Output /M

$1.16/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

1.7s

Throughput

44 tps

GLM 4.5V

z-ai/glm-4.5v

Context

64k

Input /M

$0.60/M

Output /M

$1.80/M

Cache read /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GLM 4.5V Thinking

z-ai/glm-4.5v:thinking

Context

64k

Input /M

$0.60/M

Output /M

$1.80/M

Cache read /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GLM 4.6

FP4

z-ai/glm-4.6:zai

Context

203k

Input /M

$0.63/M

Output /M

$2.31/M

Cache read /M

$0.12/M

Cache hit

N/A

TTFT

9.3s

Throughput

25 tps

GLM 4.6 (Thinking)

FP4

z-ai/glm-4.6:thinking:zai

Context

203k

Input /M

$0.63/M

Output /M

$2.31/M

Cache read /M

$0.12/M

Cache hit

56.8%

TTFT

9.3s

Throughput

25 tps

GLM 4.6V Original

z-ai/glm-4.6v-original

Context

128k

Input /M

$0.60/M

Output /M

$0.90/M

Cache read /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GLM 4.7

FP4

z-ai/glm-4.7:zai

Context

203k

Input /M

$0.63/M

Output /M

$2.31/M

Cache read /M

$0.12/M

Cache hit

N/A

TTFT

9.2s

Throughput

24 tps

GLM 4.7 (Thinking)

FP4

z-ai/glm-4.7:thinking:zai

Context

203k

Input /M

$0.63/M

Output /M

$2.31/M

Cache read /M

$0.12/M

Cache hit

39.9%

TTFT

9.2s

Throughput

24 tps

GLM 5

FP8

z-ai/glm-5:zai

Context

203k

Input /M

$1.05/M

Output /M

$3.36/M

Cache read /M

$0.21/M

Cache hit

0%

TTFT

7s

Throughput

51 tps

GLM 5 (Thinking)

FP8

z-ai/glm-5:thinking:zai

Context

203k

Input /M

$1.05/M

Output /M

$3.36/M

Cache read /M

$0.21/M

Cache hit

0%

TTFT

7s

Throughput

51 tps

GLM 5.1

FP8

z-ai/glm-5.1:zai

Context

203k

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

Cache hit

43.2%

TTFT

9.6s

Throughput

23 tps

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:zai

Context

203k

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

Cache hit

33.5%

TTFT

9.6s

Throughput

23 tps

GLM 5.2

FP8

z-ai/glm-5.2:zai

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

Cache hit

4.1%

TTFT

2.4s

Throughput

62 tps

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:zai

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

Cache hit

4.1%

TTFT

2.4s

Throughput

62 tps

GLM 5.3

FP8

z-ai/glm-5.3:zai

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

Cache hit

72.1%

TTFT

2.9s

Throughput

53 tps

GLM 5.3 (Thinking)

FP8

z-ai/glm-5.3:thinking:zai

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

Cache hit

46.1%

TTFT

2.9s

Throughput

53 tps

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:zai

Context

1.0M

Input /M

$0.16/M

Output /M

$0.53/M

Cache read /M

$0.03/M

Cache hit

91.5%

TTFT

3.9s

Throughput

31 tps

Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using Z.AI via the API

Call a model served by Z.AI using its displayed model ID, including the provider suffix when selection is supported.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/GLM-4.5-Air:zai",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :zai to the model ID, set "provider": "zai" in the request body, or send an X-Provider: zai header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

See the API documentation for provider preferences, price-aware routing, and error behavior.