Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
OpenAI
openai/gpt-oss-20bCatalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
OpenAI
gpt-oss-20b earns a request when it needs step-by-step reasoning, tool calls, running on your own hardware; a short, general request would go to Nemotron 3.5 Super VL (free) instead - free per million input tokens against $0.02 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points.
1 target runs this model; traffic is measured over the last 30 days.
Photo: RDNE Stock project
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Cached input reads $0.009 per 1M · weights on Hugging Face as openai/gpt-oss-20b
A higher intelligence index, best first, with the price it comes at.
from openai import OpenAI
client = OpenAI(base_url="https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/v1", api_key="osr_live_...")
resp = client.chat.completions.create(
model="gpt-oss", # the target on this deployment that runs gpt-oss-20b
messages=[{"role": "user", "content": "Summarise this in one sentence."}],
)
print(resp.model, resp.choices[0].message.content)Input list price per million tokens; gpt-oss-20b is the cheapest of 13 listed.
Other models by the same vendor in the catalogue.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.