Skip to content
All models
llmollama/gpt-oss:20b
OpenAI

gpt-oss-20b (self-hosted)

OpenAI gpt-oss-20b · gpt-oss

OpenAI's open-weight 20B reasoning model under Apache-2.0, served on our own hardware - strong general reasoning, coding and agentic tool use without data leaving the deployment.

Executable through /v1/chat/completions On Prem boundary PII allowed Tool calling
Price per 1M tokens
$0.40
$0.0004 per 1k
Requests · 30d
1
new
Latency
29.4 ms
measured · declared 1800 ms
Success rate
100.0%
quality prior 0.78

Underlying model

Published by the vendor; the platform bills at the target's declared price.

OpenAI

gpt-oss-20b

reasoning open weights tools

OpenAI openai/gpt-oss-20b

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...

Input $/1M
$0.03
Output $/1M
$0.13
Context
131K
Max output
118K
Released
Aug 5, 2025
Modalities
text
Intelligence index9
Coding index21
Agentic index1

Cached input reads $0.03 per 1M · weights on Hugging Face as openai/gpt-oss-20b

Traffic over 30 days

Requests per day this target answered on this deployment, with the cost line.

  • requests (peak 1)
  • failed
Tokens
0
Spend
$0
Previous window
0 req

Routed for

Domains the signal layer detected on requests that ended here.

  • General1 · 100%

Capabilities

DomainsGeneral, Marketing, Finance
ActionsReasoning, Generation, Summarize, Qa
Complexity band0.35 - 0.70
Languages*
Context window128K tokens
Streamingyes

Policy constraints

Hard stops enforced before scoring.

Data boundaryOn Prem
RegionsUS
PIIallowed
Max input tokensunlimited
Tenantsall

Representative prompts

Examples the similarity strategy matches against.

  • Explain the trade-offs between speculative decoding and batching for a 20B model on one GPU.
  • Draft a technical blog post comparing three open-weight models for on-prem agents.
  • Plan the steps an agent needs to migrate a Flask app to FastAPI.

Call it

Pin this target with model="gpt-oss", or send a candidate list and let the router choose and fall back.

curlbash
curl https://api.opensmartroute.ai/v1/chat/completions \
  -H "Authorization: Bearer $OSR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-oss", "messages": [{"role": "user", "content": "Explain the trade-offs between speculative decoding and batching for a 20B model on one GPU."}]}'
OpenAI SDKpython
from openai import OpenAI

client = OpenAI(base_url="https://api.opensmartroute.ai/v1", api_key="osr_live_...")
resp = client.chat.completions.create(
    model="gpt-oss",            # pin this target, or "auto" to let the router choose
    messages=[{"role": "user", "content": "Explain the trade-offs between speculative decoding and batching for a 20B model on one GPU."}],
    extra_body={"models": ["gpt-oss", "auto"]},   # fall back to the router's pick if it fails
)
print(resp.model, resp.choices[0].message.content)
gpt-oss-20b (self-hosted) (gpt-oss) - OpenSmartRoute