GLM API pricing & models

Zhipu · 3 live models

SoleAPI serves 3 Zhipu models: GLM-5.3-Flash, GLM-5.2, GLM-5.3. Input costs 0.48–4.8 Credits / M tokens (1 Credit = ¥1), up to 40% below list price. Compatible with Anthropic Messages; one API key for all of them, pay as you go.

Live models
3
Lowest input price
0.48Credits / M
Largest context
1Mtokens
Avg. 7-day uptime
100.0%

Zhipu model pricing

SoleAPI default channel price in Credits (1 Credit = ¥1); struck-through is the list price. Click a model for full pricing, protocols and uptime.

ModelContext · outputInput / MOutput / M7-day uptime
GLM-5.3-Flashglm-5.3-flash1M · 128K$0.1210.4840% off$0.4221.68—
GLM-5.2glm-5.21M · 128K$1.214.840% off$4.2216.8—
GLM-5.3glm-5.31M · 128K$1.214.840% off$4.2216.8100.0%

Input (prompt) / Output (completion) are per 1M tokens; image and video models show their primary unit price. Uptime comes from SoleAPI probes; a dash means not probed yet.

How to call Zhipu models

Samples use GLM-5.3-Flash; change the model field to call any other model from this vendor.

Anthropic SDK or any Messages-protocol client: point base_url at https://api.soleapi.com and use a SoleAPI key.

curl https://api.soleapi.com/v1/messages \
  -H "x-api-key: $SOLEAPI_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Explain prompt caching in one sentence"}]
  }'

Zhipu model capabilities

Exactly as flagged in the catalog.

CapabilityGLM-5.3-FlashGLM-5.2GLM-5.3
Vision
Function Calling
Reasoning
Prompt Caching
Response Schema
Audio
Video
File Input
Streaming
Web Search
Realtime
Session
Media
Multipart Form
Binary Response

Compare Zhipu models

Pricing, context, capabilities and uptime side by side.

FAQ

How much does the GLM API cost on SoleAPI?

Zhipu models cost 0.48–4.8 Credits / M input tokens, with 1 Credit = ¥1; the cheapest is GLM-5.3-Flash. That is up to 40% below list price — see the table above.

How do I call GLM models on SoleAPI with the official SDK?

Point the base URL at https://api.soleapi.com and use a SoleAPI key. Anthropic Messages are supported and request bodies are identical to the official API.

Which GLM model has the largest context window?

GLM-5.3-Flash, with 1M tokens. Context and max output for every model are in the pricing table above.

Can I pay for the GLM API with Alipay?

Yes. SoleAPI accepts Alipay top-ups; 1 Credit = ¥1, billed per use with no monthly fee or minimum.

One API key for every Zhipu model

Free credits on sign-up, pay as you go, no monthly fee.

Get an API Key