DeepSeekPay as you go

DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Model ID

deepseek/deepseek-v4-flash-0731
Context window
1.05M
tokens
Max output
128K
tokens
Input
$0.091
per 1M tokens
Output
$0.182
per 1M tokens

Cache read $0.0182 · Cache write $0.091

Quickstart

Call DeepSeek V4 Flash 0731 in one request.

Point the SDK you already use at xKiro and pass the model ID. The same key works for every model in the catalog.

SDK guides
main.py
import osfrom openai import OpenAI client = OpenAI(    api_key=os.environ["XKIRO_API_KEY"],    base_url="https://api.xkiro.com/v1",) res = client.chat.completions.create(    model="",    messages=[        {"role": "user", "content": "Explain HTTP caching in two sentences."},    ],) print(res.choices[0].message.content)
Response · Example

✓ 200 OK

"model": "deepseek/deepseek-v4-flash-0731"

HTTP caching stores copies of responses so later requests can be served without contacting the origin server. Headers such as Cache-Control and ETag decide how long a copy stays fresh and how it is revalidated.

14 input · 42 output tokens · $0.0000089 at this model’s rates

Create an API key in the dashboard and export it as XKIRO_API_KEY.

Pricing

What DeepSeek V4 Flash 0731 costs.

Billed per million tokens from your wallet balance, outside plan budgets.

  • $0.091

    $0.14−35%

    Input

    per 1M tokens

  • $0.182

    $0.28−35%

    Output

    per 1M tokens

  • $0.0182

    Cache read

    per 1M tokens

  • $0.091

    Cache write

    per 1M tokens

Requires an account that has paid — subscribe to a plan or top up your wallet.

Billed fairly

  • A request that fails before any output is generated is never billed
  • An identical blocking request retried within two minutes replays the first result — no double charge
  • If a stream breaks off or you cancel it, you pay only up to that point

Specifications

Limits and capabilities.

Context window
1,048,576 tokens
Max output
128,000 tokens
Input
Text
Output
Text
Provider
DeepSeek
Model ID
deepseek/deepseek-v4-flash-0731
Good for
Coding · Long context

Capabilities

  • Tool useSupported
  • VisionNot supported
  • Video inputNot supported
  • ReasoningSupported

Reasoning effort

No reasoning control: reasoning parameters are ignored by this model.

Reasoning guide

Supported parameters

  • max_tokens
  • temperature
  • top_p
  • stop
  • frequency_penalty
  • presence_penalty
  • seed
  • stream
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • reasoning
  • include_reasoning

Compare

Similar models.

Closest in price and context window — same provider first, then alternatives from other providers.

Browse all 69 models
DeepSeek V4 Flash 0731 compared with similar models, prices per 1M tokens
ModelInput / 1MOutput / 1M
DeepSeek V4 Flash 0731This model−35%Pay as you goReasoning · Tool use1.05M$0.091$0.14$0.182$0.28$0.0182
DeepSeek V4.1 Flash−50%Pay as you goVision · Reasoning · Tool use1.05M$0.075$0.15$0.3$0.6$0.0015
DeepSeek V4 Pro 0813−35%Pay as you goReasoning · Tool use1.05M$0.2828$0.435$0.5655$0.87$0.0023
GPT-6 LunaVision · Reasoning · Tool use1.05M$0.1$0.5$0.01
Haiku 5.5NewVision · Reasoning · Tool use1M$0.1$0.5$0.01
GPT-5.6 Luna−50%Vision · Reasoning · Tool use1M$0.1$0.2$0.6$1.20$0.05
Nemotron 3.5 Super VLVision · Reasoning · Tool use1M$0.15$0.5$0.02
modeldeepseek/deepseek-v4-flash-0731

Start building with DeepSeek V4 Flash 0731.

Create a key, point your SDK at xKiro and call deepseek/deepseek-v4-flash-0731.

No credit card · No auto-renewal · 26 free models, free forever