DeepSeek V4.1 Flash 1017
everyais/deepseek-v4-1-flash-1017
DeepSeek V4.1 Flash 1017 by DeepSeek: 1.0M context, text and image in, text out. See its current price and call it through everyais with a single API key.
You can also call it as: deepseek-v4-1-flash-1017
75% offInput Text · ImageOutput Text
Available now
- Model type
- Chat
- Released
- Not yet published
- Price unit
- Per 1M tokens
- Context window
- 1.0M
- Maximum output
- Not yet published
- Model reference price (USD)
- Input / 1M tokens
$0.3$0.075- Output / 1M tokens
$1.2$0.3- Cache read / 1M tokens
$0.006$0.0015- Cache write / 1M tokens
$0.12$0.03
Capabilities
- ✓ Streaming
- ✓ Tool use
- ✓ Vision
- ✓ Reasoning
Supported APIs
Usage and availability trend
Daily tokensInputOutput
Last 11 days · 2026-10-28 Input 12,100,252 · Output 4,488,575 tokens (partial day in progress).
Daily availability (success rate %)
A gap means that day's sample was too small to publish a success rate; it does not mean 0%.
Code example
The API key is read from the EVERYAIS_API_KEY environment variable.
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["EVERYAIS_API_KEY"],
base_url="https://api.everyais.com/v1",
)
response = client.chat.completions.create(
model="everyais/deepseek-v4-1-flash-1017",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Related models
Compare models side by side
Compare capabilities, context windows, and reference prices to find a model for your use case. Your actual billed rate can differ by account.
Pricing and specs: public catalog · updated