How much does DeepSeek V4 Pro cost on Velqa?

DeepSeek V4 Pro costs $1.528 per million input tokens and $3.055 per million output tokens, in USD. It is available on the Pro plan.

Can I use DeepSeek V4 Pro without a subscription?

Yes. DeepSeek V4 Pro can be called with prepaid Boost credit, without a monthly plan. Trying it in the playground does need an account, though: anonymous playground access is limited to the demo model.

Is DeepSeek V4 Pro compatible with the OpenAI API?

Yes. Point your client at https://api.velqa.dev/v1 and set the model to "deepseek-v4-pro" — DeepSeek V4 Pro answers on the standard chat completions endpoint, streaming included.

DeepSeek V4 Pro API — pricing and access

Flagship raisonnement lourd

Input: $1.528 USD / 1M tokens
Output: $3.055 USD / 1M tokens
Context: 160k
Available on: Pro
Provider: DeepSeek

DeepSeek V4 Pro is the catalog's flagship heavy-reasoning model: contract analysis, code review on an existing codebase, summarizing a financial report, anything that needs to hold several constraints in mind across a long answer. It's only available from the Pro plan up, and its 160k window absorbs a full document.

Against Qwen3.7 Max, its direct competitor at the same Pro tier and a very close price, the choice mostly comes down to context: Qwen3.7 Max reaches 256k where DeepSeek V4 Pro stops at 160k, which matters for a very large document. Against DeepSeek V4 Flash, its cheaper sibling in the same family, the difference is much more reliable reasoning at a noticeably higher cost per token.

It is not the right choice for high-volume chat or repeated short answers: the cost climbs fast without the extra quality being put to use, and DeepSeek V4 Flash covers that case for a fraction of the price. It's also not a coding-agent specialist: Kimi K2.6 is built specifically for autonomous development sessions.

Measured on Velqa

Time to first token: 0.81 s
Throughput: 25.3 tokens/s

Median of 5 streamed calls against api.velqa.dev, 2026-08-10.

Call it

OpenAI-compatible endpoint — change the base URL and the model id, nothing else.

curl https://api.velqa.dev/v1/chat/completions \
  -H "Authorization: Bearer $VELQA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related models

FAQ

How much does DeepSeek V4 Pro cost on Velqa?: DeepSeek V4 Pro costs $1.528 per million input tokens and $3.055 per million output tokens, in USD. It is available on the Pro plan.
Can I use DeepSeek V4 Pro without a subscription?: Yes. DeepSeek V4 Pro can be called with prepaid Boost credit, without a monthly plan. Trying it in the playground does need an account, though: anonymous playground access is limited to the demo model.
Is DeepSeek V4 Pro compatible with the OpenAI API?: Yes. Point your client at https://api.velqa.dev/v1 and set the model to "deepseek-v4-pro" — DeepSeek V4 Pro answers on the standard chat completions endpoint, streaming included.