Authors and ModelsDeepSeek

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash
DeepSeek · Text Generation
POST /v1/chat/completions

Lightweight flagship of DeepSeek’s new architecture with native image understanding, hybrid thinking, 1M context, and up to 384K output tokens.

At a glance

FieldValue
Model iddeepseek-v4-1-flash
Model release date2026-09-10
Input modalitiesText, Image
Output modalitiesText
Context window1M
Weight precision-
Max output tokens393,216
RegionSingapore
Featuresreasoning, vision, function_calling, agentic_coding
Native inferenceNo
NewYes
Structured outputJSON Mode
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/deepseek-v4-1-flash:generateContent
Alternate model idsdeepseek-v4.1-flash, deepseek/deepseek-v4-1-flash, deepseek-ai/deepseek-v4-1-flash

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$0.30
Outputper 1M generated tokens$1.20
Web Search (Linkup)per call when invoked$0.013

Example request

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "deepseek-v4-1-flash", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno0.7Sampling temperature. 0 = deterministic, 2 = maximum randomness. · Range: 0 – 2
top_pnumberno0.9Nucleus sampling probability mass. Lower = more focused. · Range: 0 – 1
max_tokensnumberno4096Maximum output tokens. · Range: 1 – 393216
stopstringno-Up to 4 strings where the model will stop generating further tokens.
enable_thinkingbooleannotrueEnable step-by-step reasoning before answering.
thinking_budgetnumberno32768Maximum tokens reserved for the reasoning process. Up to 393216. · Range: 1 – 393216
reasoning_effortenumno"medium"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service. · Allowed: none, low, medium, high, max
response_formatenumno-Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.
web_search_linkupbooleannofalseOptional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds $0.013 per call when invoked on top of the model’s normal token cost. Disabled by default.
disable_formattingbooleannofalseWhen enabled, the gateway will not append the “Sources” footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.

Notes

Thinking is enabled by default and can be disabled. Reasoning tokens are billed as output tokens. Image input is accepted alongside text. JSON mode is supported. Strict JSON Schema output is not available on this model. Optional Linkup web search is billed only when invoked.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/deepseek-v4-1-flash.