Use GLM 5.3 in Cline
Cline runs GLM 5.3 on OceanToken with three settings: a base URL, your key and the model id. Tested on October 18, 2026 with Cline CLI 3.0.73.
Settings
| Setting | Value |
|---|---|
| API Provider | OpenAI Compatible |
| Base URL | https://api.oceantoken.ai/v1 |
| API Key | your OceanToken API key |
| Model ID | z-ai/glm-5.3 |
| Supports Images | Off |
| Context Window Size | 1,048,576 |
| Max Output Tokens | 32,000 |
From the command line
cline auth openai-compatible -k "$OCEANTOKEN_API_KEY" -b https://api.oceantoken.ai/v1 -m z-ai/glm-5.3
cline "Reply with the single word OK"What it costs
An agent resends a long prompt on every turn, so the cached input price matters as much as the input price. GLM 5.3 caches the repeated part of the prompt on its own: from the second turn of a task it is billed at the cached input price.
About these prices
Frequently asked questions
Does GLM 5.3 work with Cline’s tools?
Yes. It was tested on October 18, 2026 with Cline CLI 3.0.73: tool calls and streaming.
How much does GLM 5.3 cost in Cline?
Every request Cline makes is billed at the model’s price: $1.19 / $3.74 per 1M input / output tokens. The repeated part of a long prompt is billed at $0.26 per 1M cached input tokens. Each request’s charge is in the console under Logs.
Where do I put my OceanToken key?
Create a key in the OceanToken console and give it a credit limit: an agent sends many requests, and the limit caps what this key can spend. Keep it in an environment variable, never in a file in your repository.
Other models tested with Cline
Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Haiku 4.5 · GPT-5.5 · DeepSeek V4 Pro · DeepSeek V4.1 Flash · Qwen3.8 Flash
GLM 5.3 in other tools
Keep exploring
GLM 5.3 vs DeepSeek V4 Pro · GLM 5.3 vs Kimi K3 · GLM 5.3 vs Claude Sonnet 5.5 · GLM 5.3 vs Claude Opus 5.5 · Cheaper alternatives to GLM 5.3