DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is the GA release of DeepSeek V4 Pro, a large-scale Mixture-of-Experts model with a 1M-token context window, tuned for reasoning, coding, and long-horizon agent workflows.
Model ID
deepseek/deepseek-v4-pro-0813- Context window
- 1.05M
- tokens
- Max output
- 128K
- tokens
- Input
- $0.2828
- per 1M tokens
- Output
- $0.5655
- per 1M tokens
Cache read $0.0023 · Cache write $0.2828
Quickstart
Call DeepSeek V4 Pro 0813 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-pro-0813"
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 · $0.000028 at this model’s rates
Create an API key in the dashboard and export it as XKIRO_API_KEY.
Pricing
What DeepSeek V4 Pro 0813 costs.
Billed per million tokens from your wallet balance, outside plan budgets.
$0.2828
$0.435−35%Input
per 1M tokens
$0.5655
$0.87−35%Output
per 1M tokens
$0.0023
Cache read
per 1M tokens
$0.2828
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 Pro 0813 at $0.66 / $1.98 per 1M tokens.
Pay as you go here: 57% less than the official API.
DeepSeek pricing page (lowest tier), checked Oct 21, 2026Billed 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-pro-0813
- 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 guideSupported parameters
- max_tokens
- temperature
- top_p
- stop
- frequency_penalty
- presence_penalty
- seed
- stream
- tools
- tool_choice
- reasoning
- include_reasoning
Compare
Similar models.
Closest in price and context window — same provider first, then alternatives from other providers.
Browse all 69 models| Model | Input / 1M | Output / 1M | ||
|---|---|---|---|---|
| 1.05M | $0.2828 | $0.5655 | $0.0023 | |
| 1.05M | $0.091 | $0.182 | $0.0182 | |
| 1.05M | $0.075 | $0.3 | $0.0015 | |
| 1M | $0.195 | $1.63 | $0.0195 | |
| 1M | $0.4875 | $2.44 | $0.0488 | |
| 1M | $0.4875 | $2.44 | $0.0488 | |
| 1M | $0.4875 | $2.44 | $0.0488 |
Start building with DeepSeek V4 Pro 0813.
Create a key, point your SDK at xKiro and call deepseek/deepseek-v4-pro-0813.
No credit card · No auto-renewal · 26 free models, free forever