GPT-5.4

OpenAI · openai/gpt-5.4

Available

Earlier GPT-5-series flagship for coding and professional work, with reasoning off by default.

Input / 1M tokens

৳307.53

Output / 1M tokens

৳1,845.15

Cached input / 1M

৳30.75

Context length

1.05M

Max output

128K

Provider list price: $2.50 in · $15.00 out per 1M tokens (OpenAI), × ৳123.01 per dollar. No markup. A prompt over 272K tokens is billed at ৳615.05 in · ৳2,767.73 out per 1M for the whole request — the provider's own long-context price.

Suitable for

Reasoning
Coding
Vision
Agents
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": "openai/gpt-5.4",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Try in Playground Docs for this model

Performance

Throughput65 tok/s

Time to first token1.5s

StreamingSupported

Tool callingSupported

Typical figures for this model, which the auto/* routers score on — not a guarantee for any one request.

Routing

Primary routeOpenAI direct

Fallback hostsNone — one host

Prompt retentionPadma keeps none unless you turn on payload logging; the provider's own API terms apply