GLM 5

Name: GLM 5
Brand: Z.ai
SKU: glm-5
Availability: InStock

Live

Z.ai198K context · Text, Reasoning

Use this model

Best discount now99.0%offYou pay 1.0% of reference.

Median discount75.0%offAcross 183 live offers.

Realized · 7 daysNot enough dataIt fills in after the nightly update.

Requests · 24h48,613183 offers from 72 sellers.

Current offers

182 of 663 offers

Availability

Providers

Sort by

ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining

Amazon Bedrock

99%

$0.00594 in

$0.0190 out

916ms

94.8%

∞

Amazon Bedrock

99%

$0.00594 in

$0.0190 out

916ms

94.8%

∞

$0.269

∞

Amazon Bedrock

99%

$0.00594 in

$0.0190 out

916ms

94.8%

∞

$0.040

∞

Amazon Bedrock

99%

$0.00594 in

$0.0190 out

916ms

94.8%

∞

Z.ai

99%

$0.00594 in

$0.0190 out

5.5s

68.7%

∞

$21

∞

Amazon Bedrock

99%

$0.00594 in

$0.0190 out

916ms

94.8%

∞

Amazon Bedrock

99%

$0.00600 in

$0.0192 out

916ms

94.8%

∞

$0.087

∞

Amazon Bedrock

99%

$0.00600 in

$0.0192 out

916ms

94.8%

∞

Z.ai

99%

$0.00600 in

$0.0192 out

5.5s

68.7%

∞

$28

∞

Z.ai

99%

$0.00600 in

$0.0192 out

5.5s

68.7%

∞

Total

Cumulative offers

Offered

∞

Sold

$192

Remaining

∞

Discount trend

Realized · 7 days

No trend yet.It fills in after the nightly update.

Recent fills

17:105,114 tokensZ.ai direct93.0%

17:105,337 tokensZ.ai direct93.0%

17:094,970 tokensZ.ai direct99.0%

17:0918,295 tokensZ.ai direct93.0%

17:095,641 tokensZ.ai direct99.0%

17:094,706 tokensZ.ai direct99.0%

17:094,804 tokensZ.ai direct99.0%

17:094,703 tokensZ.ai direct99.0%

Settled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic

Route	p50 latency	p95 latency	Throughput	Success rate	ShareShare of traffic
Z.ai direct	24.87 s	82.59 s	99 tok/s	68.7%	95%
Venice AI direct	1.67 s	24.87 s	40 tok/s	90.4%	2%
OpenRouter	2.25 s	18.42 s	243 tok/s	16.5%	1%
Google Vertex	4.11 s	82.59 s	54 tok/s	100.0%	1%
AWS Bedrock	679 ms	13.64 s	599 tok/s	94.8%	1%
Mordiem	—	—	—	1.1%	0%

Z.ai direct95% of traffic

68.7% success

p50 24.87 s · p95 82.59 s · 99 tok/s

Venice AI direct2% of traffic

90.4% success

p50 1.67 s · p95 24.87 s · 40 tok/s

OpenRouter1% of traffic

16.5% success

p50 2.25 s · p95 18.42 s · 243 tok/s

Google Vertex1% of traffic

100.0% success

p50 4.11 s · p95 82.59 s · 54 tok/s

AWS Bedrock1% of traffic

94.8% success

p50 679 ms · p95 13.64 s · 599 tok/s

Mordiem0% of traffic

1.1% success

p50 — · p95 — · —

Use this model

Change your base URL.
Keep your code.

Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.

Read the quickstart ↗

curl https://api.surplusintelligence.ai/v1/chat/completions \
  -H "Authorization: Bearer $SURPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

curl $SURPLUS_BASE_URL/chat/completions \
  -H "Authorization: Bearer $SURPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1

GLM 5

Discount trend

Recent fills

Performance by provider route · 24h

Change your base URL.Keep your code.

Related models

Change your base URL.
Keep your code.