Run Qwen3.8 27B Xploded in Continue
Run qwen3.8-27b-xploded in Continue through Wild West API: one key, a hard spend cap, and a model that answers instead of refusing.
| Model id | qwen3.8-27b-xploded |
|---|---|
| Context window | 524,288 tokens (524K) |
| Tool calling | Supported |
| Price per 1M tokens | $0.30 input, $0.25 on a cache hit, $2.40 output |
| Intelligence | 34 on the Artificial Analysis Intelligence Index v4.3.2, for the base model |
| Web search | Add :online to the id |
Set it up
- Add a model block to ~/.continue/config.yaml with model: qwen3.8-27b-xploded 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: Qwen3.8 27B Xploded (Wild West API) provider: openai model: qwen3.8-27b-xploded apiBase: https://wildwestapi.com/v1 apiKey: ${{ secrets.WILDWEST_API_KEY }} defaultCompletionOptions: contextLength: 524288 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), Qwen3.8 27B Xploded comes to about $0.25 at today's prices; the cache price does most of the work, since re-read context is billed at $0.25 rather than $0.30 per million.
FAQ
Can Qwen3.8 27B Xploded 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 $0.25 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, $2.40 out and $0.25 per million on cache hits. Put a spend cap on the key so a long run cannot overrun it.
Is it uncensored?
A small, cheap uncensored Qwen with half a million tokens of context and tool calling. The budget pick for agents.