Z.AI

SG

15 models available

Models served by Z.AI

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	Latency	Throughput
GLM 4.5 Air FP8	128k	$0.21/M	$1.16/M	$0.03/M	43.4%	0.6s	46 tps
GLM 4.5 Air (Thinking) FP8	128k	$0.21/M	$1.16/M	$0.03/M	0.4%	0.6s	46 tps
GLM 4.6 FP4	200k	$0.63/M	$2.31/M	$0.12/M	0%	1s	40.5 tps
GLM 4.6 (Thinking) FP4	200k	$0.63/M	$2.31/M	$0.12/M	34.9%	1s	40.5 tps
GLM 4.7 FP4	200k	$0.63/M	$2.31/M	$0.12/M	0%	1.8s	29 tps
GLM 4.7 (Thinking) FP4	200k	$0.63/M	$2.31/M	$0.12/M	4.3%	1.8s	29 tps
GLM 5 FP8	200k	$1.05/M	$3.36/M	$0.21/M	0%	1.2s	62 tps
GLM 5 (Thinking) FP8	200k	$1.05/M	$3.36/M	$0.21/M	49.2%	1.2s	62 tps
GLM 5.1 FP8	200k	$1.47/M	$4.62/M	$0.27/M	1.5%	4s	22 tps
GLM 5.1 (Thinking) FP8	200k	$1.47/M	$4.62/M	$0.27/M	48.2%	4s	22 tps
GLM 5.2 FP8	1.0M	$1.47/M	$4.62/M	$0.27/M	6.4%	2.1s	44 tps
GLM 5.2 (Thinking) FP8	1.0M	$1.47/M	$4.62/M	$0.27/M	13.1%	2.1s	44 tps
GLM 5.3 FP8	1.0M	$1.47/M	$4.62/M	$0.27/M	23.6%	1.5s	44 tps
GLM 5.3 (Thinking) FP8	1.0M	$1.47/M	$4.62/M	$0.27/M	59.4%	1.5s	44 tps
GLM 5.3 Flash FP8	1.0M	$0.08/M	$0.26/M	$0.02/M	34.3%	3.6s	30 tps

Prices are per million tokens and include the 5% provider-selection markup. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using Z.AI via the API

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 5% markup over that provider's base price; the prices in the table above already include it.

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

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