Run GLM 5.3 Apex Outlaw in Continue
Run glm-5.3-apex-outlaw in Continue through Wild West API: one key, a hard spend cap, and a model that answers instead of refusing.
| Model id | glm-5.3-apex-outlaw |
|---|---|
| Context window | 1,048,576 tokens (1M) |
| Tool calling | Supported |
| Price per 1M tokens | $0.30 input, $0.20 on a cache hit, $1.00 output |
| Web search | Add :online to the id |
Set it up
- Add a model block to ~/.continue/config.yaml with model: glm-5.3-apex-outlaw and the Wild West API apiBase.
- Put WILDWEST_API_KEY=sk-ww-... in ~/.continue/.env; the editor extensions cannot read your shell.
- Keep capabilities: [tool_use], or Continue will not let it act in agent mode.
name: Wild West API version: 0.0.1 schema: v1 models: - name: GLM 5.3 Apex Outlaw (Wild West API) provider: openai model: glm-5.3-apex-outlaw apiBase: https://wildwestapi.com/v1 apiKey: ${{ secrets.WILDWEST_API_KEY }} defaultCompletionOptions: contextLength: 1048576 maxTokens: 32768 capabilities: - tool_use roles: - chat - edit - apply
What a session costs
For a 25-turn agent task (about 750K input tokens re-read across turns, 85% of them cache hits, 25K output), GLM 5.3 Apex Outlaw comes to about $0.19 at today's prices; the cache price does most of the work, since re-read context is billed at $0.20 rather than $0.30 per million.
FAQ
Can GLM 5.3 Apex Outlaw edit files and run commands in Continue?
Yes. Continue acts through tool calls and this model supports tool calling, so it can read, edit and run, not just chat.
What does a session cost?
About $0.19 for a 25-turn agent task (about 750K input tokens re-read across turns, 85% of them cache hits, 25K output), at $0.30 in, $1.00 out and $0.20 per million on cache hits. Put a spend cap on the key so a long run cannot overrun it.
Is it uncensored?
Apex Flash, the security-tuned GLM 5.3 Flash, with its refusals removed. For pentesting, CTFs and malware analysis: a million tokens of context, tool calling and vision.