DeepSeek V4 Pro

NEW

DeepSeek · deepseek/deepseek-v4-pro

Available

Open-weight frontier model with 1M context and 384K max output. Competitive with closed-source models at a fraction of the price.

Input / 1M tokens

৳156

Output / 1M tokens

৳468

Context length

Max output

384K

Placeholder rates. Final pricing is published per model before launch.

Suitable for

Reasoning
Coding
Long context

Example request

cURL

curl https://padmarouter.com/v1/chat/completions \
  -H "Authorization: Bearer $PADMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Try in Playground Docs for this model

Performance

Throughput55 tok/s

Time to first token1.8s

StreamingSupported

Tool callingSupported

Measured from Dhaka over the last 24h of prototype traffic.

Routing

Primary routeDeepSeek direct

FallbackSecondary region

Prompt retentionNot retained