Skip to content

GLM 5.2 · Incognito

GLM 5.2 is a large-scale reasoning model from Z.ai.

Pricing

Input
$1.32per 1M tokens
Output
$3.15per 1M tokens
Cache read
$0.231per 1M tokens
Max output
131,072tokens

Phala's price plus a 5% routing fee. Deference adds no markup.

opencode.json

{
  "provider": {
    "deference": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://deference.si/v1", "apiKey": "{env:DEFERENCE_API_KEY}" },
      "models": { "z-ai/glm-5.2:incognito": { "limit": { "context": 1048576, "output": 131072 } } }
    }
  }
}
OpenCode, set up for GLM 5.2 · Incognito