gpt-oss logo

GPT-OSS 120B API

openai/gpt-oss-120b

Call GPT-OSS 120B through UberLLM’s OpenAI-compatible API — from $0.0100/M input and $0.0600/M output, routed automatically to the cheapest healthy provider. gpt-oss · 131,072 token context. No inference markup.

Try it live — no signup
Free demo · a few prompts/day

GPT-OSS 120B pricing & providers

ProviderInput / 1MOutput / 1M
Surplus Intelligencebest$0.0100$0.0600
OpenRouter$0.0370$0.1700

How to use GPT-OSS 120B with the OpenAI SDK

Already using OpenAI or OpenRouter? Change one line — the base URL — and call GPT-OSS 120B with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uberllm.dev/v1",
    api_key="ull_your_key_here",
)

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

GPT-OSS 120B API — FAQ

How much does the GPT-OSS 120B API cost?

GPT-OSS 120B costs from $0.0100 per million input tokens and $0.0600 per million output tokens through UberLLM, which routes to the cheapest healthy provider. There is no inference markup.

How do I call GPT-OSS 120B via API?

Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "openai/gpt-oss-120b". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.

Is GPT-OSS 120B OpenAI-compatible on UberLLM?

Yes. Every model on UberLLM — including GPT-OSS 120B — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.

More gpt-oss models