GLM 5.2

Name: GLM 5.2
Brand: Z.ai
SKU: glm-5.2
Availability: InStock

Live

Z.ai1M context · Text, Tools, Reasoning

Use this model

Best discount now99.8%offYou pay 0.2% of reference.

Median discount47.0%offAcross 160 live offers.

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

Requests · 24h75,835160 offers from 70 sellers.

Current offers

160 of 613 offers

Availability

Providers

Sort by

ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining

OpenRouter

99%

$0.00036 in

$0.0103 out

2.3s

94.9%

∞

$194

∞

InferHub ?

99%

$0.00098 in

$0.0284 out

24.9s

95.3%

$115

$0.006

$115

Z.ai

99%

$0.00015 in

$0.0293 out

4.1s

66.8%

∞

$51

∞

Z.ai

99%

$0.00015 in

$0.0293 out

4.1s

66.8%

∞

$34

∞

Mistral AI

99%

$0.00015 in

$0.0293 out

∞

$0.362

∞

Z.ai

99%

$0.00015 in

$0.0293 out

4.1s

66.8%

∞

Mistral AI

99%

$0.00015 in

$0.0293 out

∞

$0.084

∞

Z.ai

99%

$0.00015 in

$0.0293 out

4.1s

66.8%

∞

Mistral AI

99%

$0.00015 in

$0.0293 out

∞

$0.022

∞

Z.ai

99%

$0.00015 in

$0.0293 out

4.1s

66.8%

∞

Total

Cumulative offers

Offered

∞

Sold

$417

Remaining

∞

Discount trend

Realized · 7 days

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

Recent fills

17:1038,485 tokensOpenRouter99.8%

17:1055,358 tokensOpenRouter99.8%

17:105,701 tokensZ.ai direct99.4%

17:1054,694 tokensOpenRouter99.8%

17:10230 tokensOpenRouter99.8%

17:106,359 tokensZ.ai direct99.4%

17:0935 tokensOpenRouter100.0%

17:094,342 tokensZ.ai direct99.4%

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	33.57 s	111.50 s	73 tok/s	66.8%	77%
OpenRouter	5.55 s	45.32 s	99 tok/s	94.9%	18%
Venice AI direct	10.11 s	45.32 s	73 tok/s	99.3%	4%
InferHub	24.87 s	82.59 s	73 tok/s	95.3%	1%
Mordiem	5.55 s	—	—	30.7%	0%

Z.ai direct77% of traffic

66.8% success

p50 33.57 s · p95 111.50 s · 73 tok/s

OpenRouter18% of traffic

94.9% success

p50 5.55 s · p95 45.32 s · 99 tok/s

Venice AI direct4% of traffic

99.3% success

p50 10.11 s · p95 45.32 s · 73 tok/s

InferHub1% of traffic

95.3% success

p50 24.87 s · p95 82.59 s · 73 tok/s

Mordiem0% of traffic

30.7% success

p50 5.55 s · 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-5.2",
    "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-5.2",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

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

GLM 5.2

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.