Run DeepSeek V4.1 Flash Lite 1017 Outlaw in Continue
Run deepseek-v4.1-flash-lite-1017-outlaw in Continue through Wild West API: one key, a hard spend cap, and a model that answers instead of refusing.
| Model id | deepseek-v4.1-flash-lite-1017-outlaw |
|---|---|
| Context window | 512,000 tokens (512K) |
| Tool calling | Supported |
| Price per 1M tokens | $0.36 input, $0.030 on a cache hit, $1.44 output |
| Intelligence | 39 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: deepseek-v4.1-flash-lite-1017-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: DeepSeek V4.1 Flash Lite 1017 Outlaw (Wild West API) provider: openai model: deepseek-v4.1-flash-lite-1017-outlaw apiBase: https://wildwestapi.com/v1 apiKey: ${{ secrets.WILDWEST_API_KEY }} defaultCompletionOptions: contextLength: 512000 maxTokens: 32768 capabilities: - tool_use roles: - chat - edit - apply
DeepSeek V4.1 Flash Lite 1017 Outlaw has its own page with every limit and price.
Uncensored DeepSeek V4.1 Flash sets it against the rest of the line, and uncensored DeepSeek goes through the DeepSeek releases one by one.
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), DeepSeek V4.1 Flash Lite 1017 Outlaw comes to about $0.096 at today's prices; the cache price does most of the work, since re-read context is billed at $0.030 rather than $0.36 per million.
FAQ
Can DeepSeek V4.1 Flash Lite 1017 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 $0.096 for a 25-turn agent task (about 750K input tokens re-read across turns, 85% of them cache hits, 25K output), at $0.36 in, $1.44 out and $0.030 per million on cache hits. Put a spend cap on the key so a long run cannot overrun it.
Is it uncensored?
DeepSeek V4.1 Flash 1017 made uncensored with the Heretic method: half a million tokens of context, tool calling, reasoning and vision. The budget DeepSeek for agents.