DeepSeekPay as you goDeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
Model ID
deepseek/deepseek-v4.1-flash- Context window
- 1.05M
- tokens
- Max output
- 128K
- tokens
- Input
- $0.075
- per 1M tokens
- Output
- $0.3
- per 1M tokens
Cache read $0.0015 · Cache write $0.075
Quickstart
Call DeepSeek V4.1 Flash 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 guidesimport 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)✓ 200 OK
"model": "deepseek/deepseek-v4.1-flash"
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 · $0.000014 at this model’s rates
Create an API key in the dashboard and export it as XKIRO_API_KEY.
Pricing
What DeepSeek V4.1 Flash costs.
Billed per million tokens from your wallet balance, outside plan budgets.
$0.075
$0.15−50%Input
per 1M tokens
$0.3
$0.6−50%Output
per 1M tokens
$0.0015
Cache read
per 1M tokens
$0.075
Cache write
per 1M tokens
Requires an account that has paid — subscribe to a plan or top up your wallet.
DeepSeek's own API lists DeepSeek V4.1 Flash at $0.15 / $0.6 per 1M tokens.
Pay as you go here: 50% less than the official API.
DeepSeek pricing page (lowest tier), checked Oct 21, 2026Billed fairly
- Requests that fail with a 5xx error are never billed
- Retrying an identical blocking request replays the first result — no double charge
- Cancel a stream and pay only for the tokens generated
Specifications
Limits and capabilities.
- Context window
- 1,048,576 tokens
- Max output
- 128,000 tokens
- Input
- Text · Image
- Output
- Text
- Provider
- DeepSeek
- Model ID
- deepseek/deepseek-v4.1-flash
- Release date
- Sep 10, 2026
- Good for
- Coding · Long context
Capabilities
- Tool useSupported
- VisionSupported
- Video inputNot supported
- ReasoningSupported
Reasoning effort
- none
- high
Set it with reasoning_effort in the OpenAI format, or thinking in the Anthropic format.
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 103 models| Model | Input / 1M | Output / 1M | ||
|---|---|---|---|---|
| DeepSeek V4.1 FlashThis model−50%Pay as you goVision · Reasoning · Tool use | 1.05M | $0.075 | $0.3 | $0.0015 |
| DeepSeek V4 Flash 0731−35%Pay as you goReasoning · Tool use | 1.05M | $0.091 | $0.182 | $0.0182 |
| DeepSeek V4 Pro 0813−35%Pay as you goReasoning · Tool use | 1.05M | $0.2828 | $0.5655 | $0.0023 |
 GPT-6 LunaVision · Reasoning · Tool use | 1.05M | $0.1 | $0.5 | $0.01 |
 Haiku 5.5NewVision · Reasoning · Tool use | 1M | $0.1 | $0.5 | $0.01 |
| GPT-5.6 Luna−50%Vision · Reasoning · Tool use | 1M | $0.1 | $0.6 | $0.05 |
 MiMo v2.6 FlashVision · Video input · Reasoning · Tool use | 1.05M | $0.14 | $0.28 | $0.0028 |
Start building with DeepSeek V4.1 Flash.
Create a key, point your SDK at xKiro and call deepseek/deepseek-v4.1-flash.
No credit card · Cancel anytime · 45 free models, free forever