GLM 4.6

Name: GLM 4.6
Brand: Z.ai
SKU: glm-4.6
Availability: InStock

Live

Z.ai198K context · Text, Tools

Use this model

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

Median discount75.0%offAcross 147 live offers.

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

Requests · 24h19,965147 offers from 62 sellers.

Current offers

147 of 593 offers

Availability

Providers

Sort by

ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining

Amazon Bedrock

99%

$0.00426 in

$0.0173 out

916ms

99.9%

∞

$30

∞

Z.ai

99%

$0.00426 in

$0.0173 out

5.5s

73.5%

∞

Z.ai

99%

$0.00426 in

$0.0173 out

5.5s

73.5%

∞

$13

∞

Z.ai

99%

$0.00426 in

$0.0173 out

5.5s

73.5%

∞

Amazon Bedrock

99%

$0.00426 in

$0.0173 out

916ms

99.9%

∞

$0.108

∞

Amazon Bedrock

99%

$0.00426 in

$0.0173 out

916ms

99.9%

∞

Amazon Bedrock

99%

$0.00426 in

$0.0173 out

916ms

99.9%

∞

Z.ai

99%

$0.00426 in

$0.0173 out

5.5s

73.5%

∞

$0.305

∞

Z.ai

99%

$0.00426 in

$0.0173 out

5.5s

73.5%

∞

$0.123

∞

Z.ai

99%

$0.00426 in

$0.0173 out

5.5s

73.5%

∞

$0.224

∞

Total

Cumulative offers

Offered

∞

Sold

$111

Remaining

∞

Discount trend

Realized · 7 days

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

Recent fills

20:1015,697 tokensAWS Bedrock99.0%

20:109,409 tokensZ.ai direct99.0%

20:1013,030 tokensZ.ai direct99.0%

20:1011,368 tokensZ.ai direct99.0%

20:095,854 tokensAWS Bedrock99.0%

20:0929,772 tokensAWS Bedrock99.0%

20:09651 tokensAWS Bedrock99.2%

20:095,312 tokensAWS Bedrock99.0%

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
AWS Bedrock	7.49 s	33.57 s	73 tok/s	99.9%	51%
Z.ai direct	33.57 s	150.53 s	1988 tok/s	73.5%	40%
Venice AI direct	2.25 s	33.57 s	30 tok/s	99.3%	8%
OpenRouter	18.42 s	274.34 s	—	17.2%	1%
Mordiem	24.87 s	—	—	48.6%	0%

AWS Bedrock51% of traffic

99.9% success

p50 7.49 s · p95 33.57 s · 73 tok/s

Z.ai direct40% of traffic

73.5% success

p50 33.57 s · p95 150.53 s · 1988 tok/s

Venice AI direct8% of traffic

99.3% success

p50 2.25 s · p95 33.57 s · 30 tok/s

OpenRouter1% of traffic

17.2% success

p50 18.42 s · p95 274.34 s · —

Mordiem0% of traffic

48.6% success

p50 24.87 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-4.6",
    "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-4.6",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

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

GLM 4.6

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.