Serve on Badgr

Serve OpenAI: gpt-oss-120b

OpenAI: gpt-oss-120b served as an OpenAI-compatible endpoint on Badgr GPU capacity.

GPU recommendation auto-generated from OpenRouter model data — not hand-verified by Badgr.

Recommended GPU

H200 141GB

Available regions

United States, Europe

Estimated cost range

$3.12 – $3.12/hr

Startup time

2–5 min

Also runs well on H100 80GB.

OpenAI-compatible API example

from openai import OpenAI

client = OpenAI(base_url="https://api.aibadgr.com/v1", api_key="YOUR_BADGR_API_KEY")

response = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Run command

badgr serve gpt-oss-120b \
  --gpu H200 \
  --max-cost 10

Context length: 131K tokens · Model ID: openai/gpt-oss-120b

Recommended Badgr routes

H100 80GB · United States

Available

from $3.12/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 2–5 min

Reliability: High

Last checked: just now

H100 80GB · United States

Available

from $3.12/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 2–5 min

Reliability: High

Last checked: just now

H100 80GB · United States

Available

from $3.12/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 2–5 min

Reliability: High

Last checked: just now

H100 80GB · United States

Available

from $3.12/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 2–5 min

Reliability: High

Last checked: just now

H100 80GB · United States

Available

from $3.12/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 2–5 min

Reliability: High

Last checked: just now

H100 80GB · Europe

Available

from $3.12/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 2–5 min

Reliability: High

Last checked: just now