DeepSeek V4 Flash | EmpirioLabs AI Docs

DeepSeek · Text Generation

POST /v1/chat/completions

Lightweight MoE model with 284B total / 13B active parameters and native 1M context, tuned for low-latency, cost-effective high-concurrency use.

At a glance

Field	Value
Model id	`deepseek-v4-flash`
Input modalities	Text
Output modalities	Text
Context window	1M
Weight precision	-
Max output tokens	393,216
Region	Germany (Frankfurt)
Features	reasoning
Native inference	No
New	Yes
Supported endpoints	`POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`

Pricing

Charge	Spec	Rate
Input	per 1M prompt tokens	$0.14
Output	per 1M generated tokens	$0.28
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-flash", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

Parameter	Type	Required	Default	Description
`temperature`	number	no	`0.7`	Sampling temperature. 0 = deterministic, 2 = maximum randomness. · Range: 0 – 2
`top_p`	number	no	`0.9`	Nucleus sampling probability mass. Lower = more focused. · Range: 0 – 1
`max_tokens`	number	no	`4096`	Maximum output tokens. · Range: 1 – 393216
`stop`	string	no	-	Up to 4 strings where the model will stop generating further tokens.
`enable_thinking`	boolean	no	true	Enable step-by-step reasoning before answering.
`thinking_budget`	number	no	`32768`	Maximum tokens reserved for the reasoning process. Up to 393216. · Range: 1 – 393216
`reasoning_effort`	enum	no	`"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`
`web_search_linkup`	boolean	no	false	Optional 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 a flat $0.013 per request on top of the model’s normal token cost. Disabled by default.
`disable_formatting`	boolean	no	false	When 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.

Variants

`:variant1`

Field	Value
Model id	`deepseek-v4-flash:variant1`
Region	Singapore
Context window	1M
Weight precision	-
Max output tokens	393,216
Features	reasoning, web_search
Native inference	No
Supported endpoints	`POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`

Pricing

Charge	Spec	Rate
Input	per 1M prompt tokens	$0.20
Output	per 1M generated tokens	$0.40
Web search	per request when enabled	$0.02

Parameters

Parameter	Type	Required	Default	Description
`temperature`	number	no	`0.7`	Sampling temperature. 0 = deterministic, 2 = maximum randomness. · Range: 0 – 2
`top_p`	number	no	`0.9`	Nucleus sampling probability mass. Lower = more focused. · Range: 0 – 1
`max_tokens`	number	no	`4096`	Maximum output tokens. · Range: 1 – 393216
`stop`	string	no	-	Up to 4 strings where the model will stop generating further tokens.
`enable_thinking`	boolean	no	true	Enable step-by-step reasoning before answering.
`thinking_budget`	number	no	`32768`	Maximum tokens reserved for the reasoning process. Up to 393216. · Range: 1 – 393216
`reasoning_effort`	enum	no	`"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`
`tool_web_search`	boolean	no	false	Enable live web search. Adds a $0.02 surcharge to the request cost when enabled.

`:variant2`

Field	Value
Model id	`deepseek-v4-flash:variant2`
Region	China
Context window	1M
Weight precision	-
Max output tokens	384,000
Features	reasoning, function_calling, web_search, cache
Native inference	No
Supported endpoints	`POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`

Pricing

Charge	Spec	Rate
Input	per 1M prompt tokens	$0.138 (was $0.14)
Output	per 1M generated tokens	$0.275 (was $0.28)
Implicit cache read	per 1M cached input tokens	$0.028
Web search	per request when enabled	$0.01

Parameters

Parameter	Type	Required	Default	Description
`temperature`	number	no	`0.7`	Sampling temperature. 0 = deterministic, 2 = maximum randomness. · Range: 0 – 2
`top_p`	number	no	`0.9`	Nucleus sampling probability mass. Lower = more focused. · Range: 0 – 1
`max_tokens`	number	no	`4096`	Maximum output tokens. · Range: 1 – 393216
`stop`	string	no	-	Up to 4 strings where the model will stop generating further tokens.
`enable_thinking`	boolean	no	true	Enable step-by-step reasoning before answering.
`thinking_budget`	number	no	`32768`	Maximum tokens reserved for the reasoning process. Up to 393216. · Range: 1 – 393216
`reasoning_effort`	enum	no	`"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`
`tool_web_search`	boolean	no	false	Enable live web search. Adds $0.01 to the request cost when enabled.

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