Hosted in Australia
DeepSeek API,
hosted in Australia.
DeepSeek V4.1 Flash behind one OpenAI-compatible API, served from dedicated GPUs in Australia. $0.30 in and $1.20 out per 1M tokens, billed per token.
Model facts
DeepSeek V4.1 Flash at a glance
Model details from DeepSeek’s own model card and API docs, as of October 2026.
| Detail | DeepSeek V4.1 Flash |
|---|---|
| Model | DeepSeek V4.1 Flash |
| Maker | DeepSeek |
| Architecture | Mixture-of-Experts with 552B backbone parameters. |
| Context window | 1M tokens. Model maker’s figure |
| Max output | Up to 384K tokens per request on DeepSeek’s own API. Model maker’s figure |
| What it’s good for | Long-context work and RAG, plus high-volume tasks such as extraction and classification. |
Sources: DeepSeek, DeepSeek V4.1 Flash model card and API models and pricing, checked 23 October 2026. Where a row says “model maker’s figure”, the limit on Xinference may differ. DeepSeek and the DeepSeek logo are trademarks of DeepSeek, shown only to identify the model. Their use does not imply endorsement.
Quickstart
Call DeepSeek V4.1 Flash from Python or curl
Your base URL and key come with your API access. Set them as environment variables, then use the OpenAI SDK or curl.
# pip install openai
import os
from openai import OpenAI
client = OpenAI(
base_url=os.environ["XINFERENCE_BASE_URL"],
api_key=os.environ["XINFERENCE_API_KEY"],
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[
{"role": "user", "content": "Extract the invoice total."},
],
)
print(response.choices[0].message.content)curl $XINFERENCE_BASE_URL/chat/completions \
-H "Authorization: Bearer $XINFERENCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"stream": true,
"messages": [{"role": "user", "content": "Hello"}]
}'
# tokens stream back as server-sent events.To move from Kimi K3 to DeepSeek V4.1 Flash, or back, change the model name.
Why Xinference
Why run DeepSeek on Xinference
One OpenAI-compatible API
DeepSeek V4.1 Flash and Kimi K3 sit behind the same endpoint. Code written for the OpenAI SDK needs a new base URL and key, not a rewrite. What an OpenAI-compatible API covers.
Hosted in Australia on dedicated GPUs
DeepSeek V4.1 Flash is served from dedicated GPUs in Australia.
Billed per token
$0.30 per 1M input tokens and $1.20 per 1M output tokens, in USD. You pay only for the tokens you use. See pricing.
No training on your data
We don’t use your prompts or outputs to train or fine-tune models unless you agree in writing. No prompt or response content kept by default.
Questions
How much does the DeepSeek V4.1 Flash API cost?
On Xinference, DeepSeek V4.1 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, in USD, billed per token. See pricing.
Is there a DeepSeek API hosted in Australia?
Yes. Xinference serves DeepSeek V4.1 Flash from dedicated GPUs in Australia, through an OpenAI-compatible API. You call it with the OpenAI SDK or curl, using the base URL and API key that come with your API access. Kimi K3 is available on the same API.
Is the DeepSeek API on Xinference OpenAI-compatible?
Yes. The Model API accepts OpenAI-format requests on /v1/chat/completions, so existing OpenAI SDK clients work with a new base URL and key. Streaming, function calling and structured output (JSON mode) go through the same API. What an OpenAI-compatible API covers.
What is the DeepSeek V4.1 Flash context window?
DeepSeek lists DeepSeek V4.1 Flash with a 1M-token context window and up to 384K output tokens on its own API, as of October 2026. Those are the model maker’s figures, and the limits on Xinference may differ.
Do you train on my data?
No. We don’t use your prompts or outputs to train or fine-tune models unless you agree in writing. No prompt or response content kept by default. This applies to Kimi K3 and DeepSeek V4.1 Flash alike. The Terms of Service and Privacy Policy set out the details.
Which DeepSeek model do you serve?
We serve DeepSeek V4.1 Flash on the Model API. For harder reasoning and agentic work, Kimi K3 is on the same API at $3.00 in and $15.00 out per 1M tokens. Don’t see the model you need? Talk to us about adding it.
Last updated