GeniusRelay
Sign upConsole

Z.ai: GLM 5.2 Thinking Private

glm-5.2-private:thinking

CompareAPIGet an API keyGet an API key

GLM 5.2 Thinking Private costs $1.63 per million input tokens and $5.13 per million output tokens, supports 1.05M context, and is available through the OpenAI-compatible API.

GLM-5.2 with thinking enabled for harder long-horizon coding, autonomous agent workflows, and complex engineering tasks.

Modalities

Text → Text

Input / output price

$1.63 / $5.13 per 1M

Context

1.05M · max output 131K

Capabilities

ReasoningTool callingLong contextOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$1.63
Output$5.13
Cached input$0.163

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00898
Per day
$4.49
Per month (30 days)
$134.75

GLM 5.2 Thinking Private: input $1.625/M · output $5.135/M · cached input $0.1625/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-5.2-private:thinking", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to glm-5.2-private:thinking.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.2-private:thinking",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is GLM 5.2 Thinking Private billed?
Input is $1.63 and output is $5.13 per million tokens; cached input is $0.163. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
1.05M tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
GLM 5.2 Thinking Private API pricing · GeniusRelay