ModelsDeep reasoning
DeepSeek V4 Pro
by DeepSeek
The larger V4. Careful maths and long proofs at a price that stays under a dollar per million out.
Input
$0.49 per 1M tokens
Output
$0.99 per 1M tokens
Specs
- Id for API calls
- deepseek-v4-pro
- Maker
- DeepSeek
- Reads
- Text
- Context
- 1M tokens
- Endpoint
- /v1/chat/completions
- Billing
- Metered per token against the key
- Served by
- A third-party model supplier, through the gateway
Once you hold a credit
- 1
Redeem it in the dashboard
A local proof covers the whole face-value set, and the balance lands on a key generated in your browser.
- 2
Call DeepSeek V4 Pro
Any OpenAI client works with the base URL https://qoura.xyz/v1 and your key.
curl https://qoura.xyz/v1/chat/completions \
-H "Authorization: Bearer qk-..." \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v4-pro", "max_tokens": 400,
"messages": [{"role": "user", "content": "Summarise this changelog"}]}'Read the privacy limits