How much does DeepSeek V4 Flash cost on Velqa?

DeepSeek V4 Flash costs $0.106 per million input tokens and $0.212 per million output tokens, in USD. It is included from the Starter plan up.

Can I use DeepSeek V4 Flash without a subscription?

Yes. DeepSeek V4 Flash can be called with prepaid Boost credit, without a monthly plan, and the playground lets you try it without an account.

Is DeepSeek V4 Flash compatible with the OpenAI API?

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

DeepSeek V4 Flash API — pricing and access

Rapide et économique — chat, Q&A, gros volume

Input: $0.106 USD / 1M tokens
Output: $0.212 USD / 1M tokens
Context: 64k
Available on: Starter and above
Provider: DeepSeek

DeepSeek V4 Flash is what we recommend for work that runs at high volume on a tight budget, and that nobody is watching a cursor for: ticket replies, field extraction, classification, form completion. It's available from Starter and its price per million tokens is among the lowest in the catalog, which matters once an application is firing thousands of calls a day. It is not the model to put behind a live chat box — see the measured latency below.

Its 64k context window is the shortest in its family: for a long document or a conversation that keeps growing, DeepSeek V4 Pro is the better move, same provider but a 160k window and noticeably stronger reasoning. Against GLM-4.7 Flash, which sits in the same price bracket, the trade is output cost against everything else: DeepSeek V4 Flash bills about half as much per million output tokens, while GLM-4.7 Flash gives you a 200k window and is far quicker both to start answering and to finish (see its own page for the measured numbers).

It is not the right choice for an agent chaining multi-step tool calls: its planning quality is limited there, and Hunyuan Hy3, available at the same Starter tier, handles that kind of task better for a still-reasonable cost.

Measured on Velqa

Time to first token: 5.56 s
Throughput: 19.4 tokens/s

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

Results announced by the provider

Terminal Bench 2.1 : 82.7 source (2026-07-31)

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-flash",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related models

FAQ

How much does DeepSeek V4 Flash cost on Velqa?: DeepSeek V4 Flash costs $0.106 per million input tokens and $0.212 per million output tokens, in USD. It is included from the Starter plan up.
Can I use DeepSeek V4 Flash without a subscription?: Yes. DeepSeek V4 Flash can be called with prepaid Boost credit, without a monthly plan, and the playground lets you try it without an account.
Is DeepSeek V4 Flash compatible with the OpenAI API?: Yes. Point your client at https://api.velqa.dev/v1 and set the model to "deepseek-v4-flash" — DeepSeek V4 Flash answers on the standard chat completions endpoint, streaming included.