Glm 5.2

silvamux/glm-5.2
Supported modalities
text
Input price$1.4 / 1M tokensper 1M tokens
Output price$4.4 / 1M tokensper 1M tokens

Pricing

Tune and Pro share the same prices.

Input contextInputOutputCache readCache write
-$1.4 / 1M tokens$4.4 / 1M tokens$0.26 / 1M tokens$1.18 / 1M tokens

Capabilities

Evaluation data not available yet

Performance

Glm 5.2 Tune

glm-5.2@tune
Last 24 hours · 34,265 requests
First token · TTFT · P50
1369ms
P95 1370 ms
Output speed · TPS · P50
38tok/s
P95 85 tok/s
Full response · E2E · P50
4.38s
P95 4.88 s
Request success rate
98.75%
33,835 completed requests
24-hour availability
24 hours ago12 hours agoNow

Glm 5.2

glm-5.2
Last 24 hours · 163,309 requests
First token · TTFT · P50
1421ms
P95 2166 ms
Output speed · TPS · P50
57tok/s
P95 98 tok/s
Full response · E2E · P50
6.12s
P95 7.14 s
Request success rate
98.97%
161,632 completed requests
24-hour availability
24 hours ago12 hours agoNow

Glm 5.2 example code and API

Tuneglm-5.2@tune
/api/v0/chat/completions/api/v1/chat/completions/api/anthropic/v1/messages
UnifiedOpenAIAnthropic
Proglm-5.2
/api/v0/chat/completions/api/v1/chat/completions/api/anthropic/v1/messages
UnifiedOpenAIAnthropic
curl https://silvamux.io/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.2",
    "messages": [{"role": "user", "content": "Hello, please introduce yourself"}]
  }'