GLM 4.7Chat
Z.ai's full GLM 4.7 reasoning model for coding and multi-step agent work.
4.4sp50100%up1 rail203K ctx$0.005typical$0.55 → $2.10 /MTok
Playground
Providers
| Provider | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|
| bbasetenNo trainingNo training on your data. Zero-retention available | 1M | $2.52 / $7.92/MTok | 2.7s | 2.7s | 100% |
Routing controls
routing.strategyproviders.onlyproviders.excludeproviders.ordermax_cost_usddata_policydocs →Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.02/req
- Input
- $2.52/M tok
- Cached input
- $0.36/M tok
- Output
- $7.92/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
glm-5.2-fast
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-fast",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is GLM 5.2 Fast?
Baseten's speed-optimized GLM 5.2 rail for real-time agentic engineering at a full 1M-token context.
How much does GLM 5.2 Fast cost?
GLM 5.2 Fast costs $2.52/M input tokens and $7.92/M output tokens.
What inputs and outputs does GLM 5.2 Fast support?
GLM 5.2 Fast accepts text and returns text.
How do I call GLM 5.2 Fast?
POST /api/v1/chat/completions with `"model": "glm-5.2-fast"`.
What other GLM models are on NinjaChat?
GLM 4.7, GLM 4.7 Flash, GLM 5.2, GLM-5.
