o4-mini

OpenAI · openai/o4-mini

Available

Reasoning-tuned model that spends extra tokens thinking before answering. Best for maths, planning and hard debugging.

Input / 1M tokens

৳132

Output / 1M tokens

৳528

Context length

200K

Max output

100K

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

Suitable for

Reasoning
Coding

Example request

cURL

curl https://padmarouter.com/v1/chat/completions \
  -H "Authorization: Bearer $PADMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/o4-mini",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Try in Playground Docs for this model

Performance

Throughput52 tok/s

Time to first token3.2s

StreamingSupported

Tool callingSupported

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

Routing

Primary routeOpenAI direct

FallbackSecondary region

Prompt retentionNot retained