- Model
glm-5v-turbo- Provider
zai- API
openai-completions- Base URL
https://api.z.ai/api/coding/paas/v4- Input
- text, image
- Reasoning
- Yes
- Context window
- 200,000
- Max tokens
- 131,072
- Cost / million input
- $0
- Cost / million output
- $0
- Cost / million cache read
- $0
- Cost / million cache write
- $0
Model config JSON
{
"providers": {
"zai": {
"apiKey": "YOUR_API_KEY",
"models": [
{
"id": "glm-5v-turbo",
"name": "glm-5v-turbo",
"reasoning": true,
"input": [
"text",
"image"
],
"contextWindow": 200000,
"maxTokens": 131072,
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"compat": {
"supportsDeveloperRole": false,
"thinkingFormat": "zai",
"zaiToolStream": true
}
}
],
"api": "openai-completions",
"baseUrl": "https://api.z.ai/api/coding/paas/v4"
}
}
}