gpt-oss-120b

CHEAP

OpenAI · openai/gpt-oss-120b

Coming soon

OpenAI's Apache-2.0 open-weight reasoning model, 117B total with 5.1B active, served by DeepInfra.

Not callable yet: Padma has not connected DeepInfra on this server. The price is real; requests answer 503 model_unavailable, and are not charged, until it is.

Input / 1M tokens

৳4.55

Output / 1M tokens

৳20.91

Cached input / 1M

no discount

Context length

131.072K

Max output

65.536K

Provider list price: $0.037 in · $0.17 out per 1M tokens (DeepInfra), × ৳123.01 per dollar. No markup.

Suitable for

Reasoning
Coding
Low Cost
Agents

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-oss-120b",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Docs for this model

Performance

Throughput150 tok/s

Time to first token0.5s

StreamingSupported

Tool callingSupported

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

Routing

Primary routeDeepInfra — its maker has no API for it

Fallback hostsNone — one host

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