GLM 4.7

Name: GLM 4.7
Brand: Z.ai
SKU: glm-4.7
Availability: InStock

Live

Z.ai128K context · Text, Reasoning

Use this model

Best discount now99.3%offYou pay 0.7% of reference.

Median discount81.7%offAcross 149 live offers.

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

Requests · 24h18,553149 offers from 58 sellers.

Current offers

149 of 630 offers

Availability

Providers

Sort by

ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining

Amazon Bedrock

99%

$0.00400 in

$0.0175 out

1.2s

100.0%

∞

$63

∞

Amazon Bedrock

99%

$0.00433 in

$0.0173 out

1.2s

100.0%

∞

Z.ai

99%

$0.00433 in

$0.0173 out

10.1s

68.9%

∞

Amazon Bedrock

99%

$0.00433 in

$0.0173 out

1.2s

100.0%

∞

Z.ai

99%

$0.00433 in

$0.0173 out

10.1s

68.9%

∞

Amazon Bedrock

99%

$0.00433 in

$0.0173 out

1.2s

100.0%

∞

Z.ai

99%

$0.00433 in

$0.0173 out

10.1s

68.9%

∞

$0.529

∞

Z.ai

99%

$0.00433 in

$0.0173 out

10.1s

68.9%

∞

Z.ai

99%

$0.00433 in

$0.0173 out

10.1s

68.9%

∞

Z.ai

99%

$0.00433 in

$0.0173 out

10.1s

68.9%

∞

$0.445

∞

Total

Cumulative offers

Offered

∞

Sold

$110

Remaining

∞

Discount trend

Realized · 7 days

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

Recent fills

20:1016,827 tokensZ.ai direct99.2%

20:09529 tokensAWS Bedrock99.6%

20:095,919 tokensAWS Bedrock99.3%

20:0916,891 tokensZ.ai direct99.2%

20:098,309 tokensAWS Bedrock99.2%

20:092,351 tokensAWS Bedrock99.2%

20:087,865 tokensAWS Bedrock99.2%

20:0810,951 tokensAWS Bedrock99.3%

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
AWS Bedrock	7.49 s	24.87 s	73 tok/s	100.0%	63%
Z.ai direct	33.57 s	111.50 s	40 tok/s	68.9%	22%
Venice AI direct	18.42 s	82.59 s	12 tok/s	99.4%	10%
OpenRouter	24.87 s	150.53 s	40 tok/s	4.2%	3%
Google Vertex	4.11 s	61.18 s	134 tok/s	87.4%	2%
Mordiem	—	—	—	1.7%	0%

AWS Bedrock63% of traffic

100.0% success

p50 7.49 s · p95 24.87 s · 73 tok/s

Z.ai direct22% of traffic

68.9% success

p50 33.57 s · p95 111.50 s · 40 tok/s

Venice AI direct10% of traffic

99.4% success

p50 18.42 s · p95 82.59 s · 12 tok/s

OpenRouter3% of traffic

4.2% success

p50 24.87 s · p95 150.53 s · 40 tok/s

Google Vertex2% of traffic

87.4% success

p50 4.11 s · p95 61.18 s · 134 tok/s

Mordiem0% of traffic

1.7% 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-4.7",
    "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-4.7",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

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

GLM 4.7

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.