DeepSeek Flash Lite Xploded in Kilo Code
Run deepseek-v4.1-flash-lite-1017-xploded in Kilo Code through MagmaRouter: one key, a hard spend cap, and a model that answers instead of refusing.
| Model id | deepseek-v4.1-flash-lite-1017-xploded |
|---|---|
| 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
- Settings, Providers, Custom provider, Provider API OpenAI Compatible.
- Base URL https://api.magmarouter.com/v1 and your key. Kilo reads https://api.magmarouter.com/v1/models and offers deepseek-v4.1-flash-lite-1017-xploded in its picker.
- For the Kilo CLI, define the same provider in kilo.json as below.
{
"provider": {
"magmarouter": {
"npm": "@ai-sdk/openai-compatible",
"options": {
"baseURL": "https://api.magmarouter.com/v1",
"apiKey": "{env:MAGMAROUTER_API_KEY}"
},
"models": {
"deepseek-v4.1-flash-lite-1017-xploded": {
"name": "DeepSeek Flash Lite Xploded",
"limit": { "context": 512000, "output": 32768 }
}
}
}
},
"model": "magmarouter/deepseek-v4.1-flash-lite-1017-xploded"
}
DeepSeek Flash Lite Xploded 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 Flash Lite Xploded 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 Flash Lite Xploded edit files and run commands in Kilo Code?
Yes. Kilo Code 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.