ltejedor/deepseek-v4.1-flash
DeepSeek V4.1 Flash 1017 (LibertAIDAI EXL3 3.5 bpw + official Engram tables) served with exllamav3 on 2x A100 80GB. Greedy chat; prompt up to 2,048 tokens, prompt + output up to 4,096. A cold start takes about 8-12 minutes.
Run ltejedor/deepseek-v4.1-flash with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
Input schema
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
Your message to the model.
|
|
| system_prompt |
string
|
|
Optional system message, placed before your prompt by the checkpoint's own chat encoder.
|
| max_tokens |
integer
|
2048
Min: 1 Max: 4096 |
Maximum tokens to generate (greedy decoding). The prompt may use up to 2,048 tokens after chat formatting, and prompt + max_tokens must stay within 4,096.
|
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 0,
"description": "Your message to the model."
},
"max_tokens": {
"type": "integer",
"title": "Max Tokens",
"default": 2048,
"maximum": 4096,
"minimum": 1,
"x-order": 2,
"description": "Maximum tokens to generate (greedy decoding). The prompt may use up to 2,048 tokens after chat formatting, and prompt + max_tokens must stay within 4,096."
},
"system_prompt": {
"type": "string",
"title": "System Prompt",
"default": "",
"x-order": 1,
"description": "Optional system message, placed before your prompt by the checkpoint's own chat encoder."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output"
}