DeepSeek V4 Flash 0731 API

Post-trained 0731 release with major gains across coding, repository work, tool use, and full-stack tasks, plus a 1M context window.

DeepSeek Text Generation 1M context Released Jul 31, 2026 Germany Proprietary Endpoint

About DeepSeek V4 Flash 0731

Post-trained 0731 release with major gains across coding, repository work, tool use, and full-stack tasks, plus a 1M context window.

Supports text input, hybrid thinking with enable_thinking and thinking_budget, function calling, strict JSON Schema output, and optional Linkup web search. Thinking tokens are billed as output tokens.

Also known as DeepSeek Flash 0731

reasoning function calling structured output agentic coding

DeepSeek V4 Flash 0731 specs

Model ID
deepseek-v4-flash-0731
Author
DeepSeek
Category
Text Generation
Released
Jul 31, 2026
Context window
1M tokens
Max output
393,216 tokens
Input
Text
Output
Text
Structured output
JSON Mode
Region
Germany
Endpoints
POST/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/deepseek-v4-flash-0731:generateContent
Alternate model IDs
deepseek/deepseek-v4-flash-0731deepseek-ai/deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.

Type
Spec
Rate
Input
per 1M prompt tokens
$0.424
Output
per 1M generated tokens
$1.272
Web Search (Linkup)
per call when invoked
$0.013
Compare on the full pricing page

How to call the DeepSeek V4 Flash 0731 API

DeepSeek V4 Flash 0731 serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id deepseek-v4-flash-0731. Get an API key from the EmpirioLabs dashboard.

cURL
curl https://api.empiriolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash-0731",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'
Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://api.empiriolabs.ai/v1",
    api_key="YOUR_EMPIRIOLABS_API_KEY",
)

response = client.chat.completions.create(
    model="deepseek-v4-flash-0731",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)
Full DeepSeek V4 Flash 0731 API reference

DeepSeek V4 Flash 0731 API parameters

Request parameters supported by the DeepSeek V4 Flash 0731 API on EmpirioLabs. Defaults apply when a field is omitted.

ParameterTypeDefaultRange / valuesDescription
temperaturenumber0.70 to 2Sampling temperature. 0 = deterministic, 2 = maximum randomness.
top_pnumber0.90 to 1Nucleus sampling probability mass. Lower = more focused.
max_tokensnumber-1 to 393216Maximum output tokens. When omitted, the model's own default applies.
stopstring--Up to 4 strings where the model will stop generating further tokens.
enable_thinkingbooleantrue-Enable step-by-step reasoning before answering.
reasoning_effortenummediumnone, low, medium, high, maxReasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model.
thinking_budgetnumber327681 to 393216Maximum tokens reserved for reasoning when thinking is enabled.
response_formatenum--Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt.
web_search_linkupbooleanfalse-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 $0.013 per call when invoked on top of the model's normal token cost. Disabled by default.
disable_formattingbooleanfalse-Return the answer without the Sources list that web search adds.

Good to know

Thinking is enabled by default and can be disabled. Reasoning tokens are billed as output tokens. Optional Linkup web search is billed only when invoked.

DeepSeek V4 Flash 0731 variants

Variants are alternate versions of DeepSeek V4 Flash 0731 with their own model id. Depending on the variant, they can differ in serving region, pricing, or supported parameters; everything else works the same way.

DeepSeek V4 Flash 0731 :variant1

Model ID
deepseek-v4-flash-0731:variant1
Region
United States
Context window
1M tokens
Structured output
JSON Schema
Type
Spec
Rate
Input
per 1M prompt tokens
$0.44
Output
per 1M generated tokens
$1.32
Web Search (Linkup)
per call when invoked
$0.013
Try :variant1 in the playground

DeepSeek V4 Flash 0731 on the blog

Announcements, prompt tests, and comparisons that cover this model.

DeepSeek V4 Flash 0731 API: common questions

How much does the DeepSeek V4 Flash 0731 API cost?

On EmpirioLabs, DeepSeek V4 Flash 0731 is billed pay as you go: Input $0.424 per 1M prompt tokens; Output $1.272 per 1M generated tokens; Web Search (Linkup) $0.013 per call when invoked. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.

What inputs and outputs does DeepSeek V4 Flash 0731 support?

DeepSeek V4 Flash 0731 takes Text as input and returns Text.

What is the context window of DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 supports a 1M-token context window with up to 393,216 output tokens per response.

Is the DeepSeek V4 Flash 0731 API OpenAI-compatible?

Yes. DeepSeek V4 Flash 0731 serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to deepseek-v4-flash-0731.

What is the model ID for DeepSeek V4 Flash 0731?

Send deepseek-v4-flash-0731 as the model in your request. The alternate IDs deepseek/deepseek-v4-flash-0731, deepseek-ai/deepseek-v4-flash-0731 also work.

When was DeepSeek V4 Flash 0731 released?

DeepSeek released DeepSeek V4 Flash 0731 on Jul 31, 2026.

Where is DeepSeek V4 Flash 0731 served from?

DeepSeek V4 Flash 0731 on EmpirioLabs is served from Germany.

Which DeepSeek V4 Flash 0731 variants are available?

DeepSeek V4 Flash 0731 is available as 2 model ids: the default deepseek-v4-flash-0731 plus deepseek-v4-flash-0731:variant1 (United States). Variants can differ in serving region, pricing, or supported parameters; the rate cards for each are on this page.

Can I try DeepSeek V4 Flash 0731 in the browser before integrating?

Yes. The EmpirioLabs playground runs DeepSeek V4 Flash 0731 in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a DeepSeek V4 Flash 0731 API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.

Compare DeepSeek V4 Flash 0731 with other models

All model comparisons

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.