LLM models
DeepSeek V4.1 Flash
On this page
DeepSeek's fast V4.1 model — thinking on by default with a non-thinking mode, a 1M-token context and up to 384K tokens of output, with JSON output, tool calls and image input.
| modelId | deepseek-v4-1-flash |
| Modality | text |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Default | deepseek-v4-1-flash | POST /api/v1/generate | prompt |
| Poll task | — | GET /api/v1/task/{id}?model=deepseek-v4-1-flash | — |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | Text value (example: A train leaves at 09:40 and arrives at 13:05, with a 25-minute stop halfway. What was its average moving speed if the route is 272 km? Show the working in… — full value in the request example) |
| reasoning_effort | string | No | How hard the model thinks before answering: Low for faster answers, Max for the deepest reasoning. (options: Low | High | Max) (example: High) |
| stream | boolean | No | Send true to receive the reply as an event stream (Content-Type: text/event-stream). Omit it and you get a single JSON response — streaming is opt-in on this endpoint. (true/false) (example: true) |
| max_tokens | number | No | Maximum response length in tokens, reasoning included. Leave empty for the default of 4,096. (range 1-128000) |
| system | string | No | System instruction for the model. Defaults to "You are DeepSeek V4.1 Flash, developed by DeepSeek." when omitted. |
| messages | array | No | A conversation instead of a single prompt: an array of { "role", "content" } objects, where role is user, assistant, system or tool (a function result, with tool_call_id); an assistant message may carry tool_calls instead of text — see tools. Send the whole conversation — we do not limit how many messages it has, and we do not drop old ones; the model's context window is the limit. Send prompt or messages, not both. Do not flatten a conversation into one prompt with "User:" / "Assistant:" labels — the model reads that as a single message, and a model using web search then searches for the whole block instead of your question. |
| tools | array | No | Functions the model may call, up to 64. Each is { "type": "function", "function": { "name", "description", "parameters" } } with parameters a JSON Schema object (the flat Responses form and Anthropic's { "name", "description", "input_schema" } are accepted too); strict: true is not accepted on this model. When the model calls one, the response carries toolCalls: run the function, then send the conversation back in messages with the assistant's tool_calls and one { "role": "tool", "tool_call_id", "content" } message per result — and the same tools again. Function calling cannot be combined with web search in the same request. |
| tool_choice | string | object | No | auto (the model decides; the default when tools is set), or none (no call). Other values are not available on this model and are refused before any charge. |
Example request
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"deepseek-v4-1-flash","input":{"prompt":"A train leaves at 09:40 and arrives at 13:05, with a 25-minute stop halfway. What was its average moving speed if the route is 272 km? Show the working in three short steps.","reasoning_effort":"High","stream":true,"max_tokens":4096}}'