DeepSeek

DeepSeek V4.1 Flash 1017 Heretic Thinking API

DeepSeek V4.1 Flash 1017 Heretic Thinking by DeepSeek through the RelaySwitch API: $0.825 per million input tokens, $3.30 per million output tokens. Pay by card or crypto (Card, USDT, USDC, BTC, ETH, SOL). No KYC.

Input / M$0.825per million tokens
Cached input / Minput rateper million tokens
Output / M$3.30per million tokens

Specs

Model id
deepseek-v4.1-flash-1017-heretic-uncensored-thinking
Developer
DeepSeek
Context window
512K tokens
Max output
128K tokens
Input
text, image

Call it

bash
1curl https://api.relayswitch.io/v1/chat/completions \
2 -H "Authorization: Bearer $RELAYSWITCH_KEY" \
3 -H "Content-Type: application/json" \
4 -d '{
5 "model": "deepseek-v4.1-flash-1017-heretic-uncensored-thinking",
6 "messages": [{"role": "user", "content": "Hello"}]
7 }'

Any OpenAI SDK works: set the base URL to https://api.relayswitch.io/v1 and the model to deepseek-v4.1-flash-1017-heretic-uncensored-thinking. Get a key or read the docs.

DeepSeek V4.1 Flash 1017 Heretic Thinking API key and pricing

One key covers DeepSeek V4.1 Flash 1017 Heretic Thinking and every other model in the catalog. Open the console with an email address, top up from $10 by card or in USDT, USDC, BTC, ETH, SOL, create a key, and send deepseek-v4.1-flash-1017-heretic-uncensored-thinking as the model. No identity check, no subscription; the balance moves only when you call.

A chat message$0.00262K tokens in, 300 out
A chat turn$0.00332K tokens in, 500 tokens out
A long document$0.047950K tokens in, 2K tokens out
A million tokens$2.0625500K in, 500K out

Costs at the live rates above; input and output billed separately, per token, from the prepaid balance.

DeepSeek V4.1 Flash 1017 Heretic Thinking in JanitorAI, SillyTavern, Chub and Risu

One 2K-in / 300-out turn on DeepSeek V4.1 Flash 1017 Heretic Thinking costs $0.0026 at today's rate; a long chat resends its history, so the price grows with the context setting. This model thinks before it answers: set max tokens to 1,000 or more in the app, or the reply comes back empty. The model field takes deepseek-v4.1-flash-1017-heretic-uncensored-thinking in every app; only the URL field differs.

text
1Proxy URL https://api.relayswitch.io/v1/chat/completions
2API key sk-relay-...
3Model deepseek-v4.1-flash-1017-heretic-uncensored-thinking
text
1Custom Endpoint (Base URL) https://api.relayswitch.io/v1
2API key sk-relay-...
3Model deepseek-v4.1-flash-1017-heretic-uncensored-thinking
text
1OpenAI Reverse Proxy URL https://api.relayswitch.io/v1
2API key sk-relay-...
3Model deepseek-v4.1-flash-1017-heretic-uncensored-thinking
text
1URL https://api.relayswitch.io/v1
2API key sk-relay-...
3Model deepseek-v4.1-flash-1017-heretic-uncensored-thinking

The same price on every model, ranked by use: best models for JanitorAI, SillyTavern and Chub.

No app? Chat with DeepSeek V4.1 Flash 1017 Heretic Thinking in the browser at Unrestrictable, with characters, images and video and no key to paste.

FAQs

DeepSeek V4.1 Flash 1017 Heretic Thinking: questions

Payment, keys and billing in short.

Open the console

A key in under a minute

Get a key

Or email hello@relayswitch.io

Run DeepSeek V4.1 Flash 1017 Heretic Thinking today

Top up by card or crypto and send "deepseek-v4.1-flash-1017-heretic-uncensored-thinking".

Join on Telegram