GPT-OSS 120B API — pricing & specs

OpenAI's open-weight model in the GPT-OSS line — a large (~120B-class) open-weights release for reasoning and coding, offered here through the OpenAI-compatible API. On KeepRouter, GPT-OSS 120B costs $0.15 per 1M input tokens and $0.60 per 1M output tokens, billed at cost with no markup and no monthly fee. Call it through the OpenAI- or Anthropic-compatible API with the model id gpt-oss-120b.

MakerOpenAI
ModalityText
Input price$0.15 per 1M tokens
Output price$0.60 per 1M tokens
CapabilitiesStreaming, Tool / function calling
APIsOpenAI-compatible & Anthropic-compatible
Model idgpt-oss-120b

How pricing works for GPT-OSS 120B

GPT-OSS 120B is billed per token — $0.15 per 1M input tokens and $0.60 per 1M output tokens. As a worked example, a 1,000-token prompt with a 500-token reply costs about $0.0004. All prices are at cost (a 0% markup) with no monthly fee.

Calling GPT-OSS 120B on KeepRouter

Point your OpenAI- or Anthropic-compatible client at KeepRouter, set the model to gpt-oss-120b, and keep the rest of your code unchanged. Streaming and tool calling work over both APIs.

cURL

curl https://keeprouter.com/v1/chat/completions \
  -H "Authorization: Bearer $KEEPROUTER_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-oss-120b","messages":[{"role":"user","content":"Hello"}]}'

Python

from openai import OpenAI
client = OpenAI(base_url="https://keeprouter.com/v1", api_key="$KEEPROUTER_KEY")
r = client.chat.completions.create(model="gpt-oss-120b", messages=[{"role":"user","content":"Hello"}])

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://keeprouter.com/v1", apiKey: process.env.KEEPROUTER_KEY });
const r = await client.chat.completions.create({ model: "gpt-oss-120b", messages: [{ role: "user", content: "Hello" }] });

Frequently asked questions

How much does GPT-OSS 120B cost on KeepRouter?

GPT-OSS 120B is $0.15 per 1M input tokens and $0.60 per 1M output tokens, billed at cost with no markup and no monthly fee.

How much does a typical GPT-OSS 120B request cost?

On KeepRouter, a 1,000-token prompt with a 500-token reply costs about $0.0004 — billed at cost with no markup.

Who makes GPT-OSS 120B?

GPT-OSS 120B is made by OpenAI. KeepRouter provides it through one OpenAI- and Anthropic-compatible API.

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

Point your OpenAI- or Anthropic-compatible client at KeepRouter and set the model to "gpt-oss-120b". It works with the OpenAI SDK, the Anthropic SDK, and Claude Code — no provider-specific SDK needed.

Does GPT-OSS 120B support streaming?

Yes. KeepRouter streams GPT-OSS 120B responses over both the OpenAI and Anthropic APIs.

Does GPT-OSS 120B support tool (function) calling?

Yes. KeepRouter passes tool calls through to GPT-OSS 120B and translates them between the OpenAI and Anthropic formats.

Guides

Related models from OpenAI

All models & pricing · Quickstart · KeepRouter vs OpenRouter · Glossary · Get an API key

Prices as of 2026-07-05.