How much does gpt-oss-120b cost per token?

gpt-oss-120b is priced at $0.03 per million input tokens and $0.15 per million output tokens, per OpenRouter as of Jul 8, 2026.

What is gpt-oss-120b's context window?

gpt-oss-120b supports a context window of up to 131.1K tokens, per OpenAI.

How widely used is gpt-oss-120b?

gpt-oss-120b accounts for about 1% of tracked OpenRouter coding-token volume as of Jul 7, 2026.

What are the alternatives to gpt-oss-120b?

By OpenRouter usage, comparable models include Gemini 2.5 Flash Lite, Laguna M.1, and Gemini 3.1 Flash Lite. Side-by-side comparisons are linked in the alternatives table.

ModelsOpenAI

gpt-oss-120b

Name: gpt-oss-120b
Author: OpenAI

openrouter hugging face price docs

Context

131.1K

tokens

Released

Aug 5, 2025

on OpenRouter

Usage rank

#18

of 41 tracked models

Token share

OpenRouter · Jul 7, 2026

Pricing

Price per million tokens

Input $/MTok

$0.03

OpenRouter · Jul 8, 2026

Output $/MTok

$0.15

OpenRouter · Jul 8, 2026

Current gpt-oss-120b prices per million tokens across tracked sources.
Source	Tracked slug	In $/MTok	Out $/MTok	Cache read	Cache write	Context	Effective	Last Δ (in)
OpenRouter	openai/gpt-oss-120b	$0.03	$0.15	—	—	131.1K	Jul 8, 2026	—
models.dev	synthetic/hf:openai/gpt-oss-120b	$0.1	$0.1	$0.1	—	131.1K	Jul 8, 2026	11.1%

latest tracked price per source · Δ = most recent input-price move within that source

2 sources tracking

Input $/MTok

Output $/MTok

per-source step lines · $/MTok

history since Jul 8, 2026

Specs

Context & availability

gpt-oss-120b specifications.
Provider	OpenAI
Context window	131.1K tokens
Listed on OpenRouter	Aug 5, 2025
Tracked price sources	models.dev · OpenRouter
Hugging Face	openai/gpt-oss-120b
OpenRouter slugs	openai/gpt-oss-120b · openai/gpt-oss-120b:free

source: OpenRouter model catalog + tracked price feeds

id: gpt-oss-120b

Usage

Share of OpenRouter tokens

90-day · to Jul 7, 2026

source: OpenRouter model rankings · share of tracked coding-token volume

1% on Jul 7, 2026

Benchmarks

Benchmark results

Benchmark scores for gpt-oss-120b.
Benchmark	Configuration	Score	Date	Source
Aider Polyglot	gpt-oss-120b (high)	41.8%	Aug 6, 2025	aider-repo
AA Coding Index	openai/gpt-oss-120b:free	30.4index	—	or-embedded-aa
AA Agentic Index	openai/gpt-oss-120b:free	13.2index	—	or-embedded-aa
AA Intelligence Index	openai/gpt-oss-120b:free	23.8index	—	or-embedded-aa
AA Coding Index	openai/gpt-oss-120b	30.4index	—	or-embedded-aa
AA Agentic Index	openai/gpt-oss-120b	13.2index	—	or-embedded-aa
AA Intelligence Index	openai/gpt-oss-120b	23.8index	—	or-embedded-aa

scores as published by each benchmark; configurations differ — compare within a row's benchmark only

Similar models

Alternatives to gpt-oss-120b by OpenRouter usage-rank proximity.
#	Model	Tokens/day	7d Δ	Head-to-head
19	Gemini 2.5 Flash LiteGoogle	78.3B	16%	vs gpt-oss-120b
21	Laguna M.1Poolside	75B	33%	vs gpt-oss-120b
18	Gemini 3.1 Flash LiteGoogle	78.7B	19%	vs gpt-oss-120b
22	Claude Fable 5Anthropic	74.6B	—	vs gpt-oss-120b

ranked by OpenRouter usage-rank proximity

snapshot Jul 7, 2026

FAQ

gpt-oss-120b FAQ

How much does gpt-oss-120b cost per token?: gpt-oss-120b is priced at $0.03 per million input tokens and $0.15 per million output tokens, per OpenRouter as of Jul 8, 2026.
What is gpt-oss-120b's context window?: gpt-oss-120b supports a context window of up to 131.1K tokens, per OpenAI.
How widely used is gpt-oss-120b?: gpt-oss-120b accounts for about 1% of tracked OpenRouter coding-token volume as of Jul 7, 2026.
What are the alternatives to gpt-oss-120b?: By OpenRouter usage, comparable models include Gemini 2.5 Flash Lite, Laguna M.1, and Gemini 3.1 Flash Lite. Side-by-side comparisons are linked in the alternatives table.

Alerts

Track gpt-oss-120b

Email me when gpt-oss-120b's price moves or it gets deprecated.