Pricing
| Provider | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|
| Morph | $1.40 | $0.26 | $4.40 |
| DeepInfra | $0.5625 | $0.105 | $1.80 |
| Novita AI | $1.40 | $0.26 | $4.40 |
| Inference.net | $1.30 | $0.20 | $4.40 |
USD, as of October 27, 2026. Live prices
GLM 5.2 API
- 1.05MContext
- 524KMax output
- $0.5625/ $1.80From, per 1M in / out
- 4Providers
Providers
Cost
| Workload | Morph | DeepInfra |
|---|---|---|
| 1,000 chat replies2K in, 500 out each | $5.00 | $2.03 |
| 1,000 agent tasks50K in, 5K out each | $92.00 | $37.13 |
| Monthly batch job500M in, 50M out | $920.00 | $371.25 |
Quickstart
curl https://api.routerplus.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-5.2",
"messages": [{ "role": "user", "content": "Hello" }]
}'FAQ
How much does the GLM 5.2 API cost?
On RouterPlus, routing for GLM 5.2 starts at Morph: $1.40 per million input tokens and $4.40 per million output tokens. The lowest listed prices are at DeepInfra: $0.5625 input and $1.80 output. Name a provider with provider.only and you pay its price. Prices as of October 27, 2026.
Which providers serve GLM 5.2?
4 providers serve GLM 5.2 on RouterPlus: Morph, DeepInfra, Novita AI and Inference.net. By default the router tries them in routing order and fails over before the first byte, never mid-answer.
What is the GLM 5.2 model ID?
Use "z-ai/glm-5.2" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.
What is the GLM 5.2 context window?
1.05M tokens of context and up to 524K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.
Is GLM 5.2 open weights?
Yes. Z.ai publishes GLM 5.2 as an open-weight model, which is why several independent providers can host it.
Do any GLM 5.2 providers retain prompts?
3 of 4 providers list no prompt retention (DeepInfra, Novita AI and Inference.net). Morph may retain prompts. Pin the providers you accept with a routing policy.
Can I reserve capacity for GLM 5.2?
Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.