GLM-5ChatNew
Zhipu AI's GLM-5 with strong bilingual (Chinese/English) capabilities.
5.4sp50100%up1 rail128K ctx$0.007typical$0.87 → $2.76 /MTok
Playground
Providers
| Provider | Role | Context | Price · in / out |
|---|---|---|---|
 fireworksNo trainingNo training on your data. Zero-retention available | Primary | 1M | $1.68 / $5.28/MToksame price, any rail |
| ddeepinfraNo trainingNo training on your data | Fallback | 1M | |
| ggmicloud |
Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.014/req
- Input
- $1.68/M tok
- Cached input
- $0.29/M tok
- Output
- $5.28/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
glm-5.2
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.2",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is GLM 5.2?
Z.AI's GLM 5.2 agentic model served directly through Fireworks' zero-retention endpoint.
How much does GLM 5.2 cost?
GLM 5.2 costs $1.68/M input tokens and $5.28/M output tokens.
What inputs and outputs does GLM 5.2 support?
GLM 5.2 accepts text and returns text.
How do I call GLM 5.2?
POST /api/v1/chat/completions with `"model": "glm-5.2"`.
What other GLM models are on NinjaChat?
GLM-5.
