GPT-OSS 120B

Pricing as of October 2026

$0.039/1M input · $0.190/1M output · 131K context · OpenAI

GPT-OSS 120B is listed at $0.039 per 1M input tokens and $0.190 per 1M output tokens from OpenAI, with a 131K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0001, or $1.34 per 10,000 requests. On that workload it is cheaper than 162 of the 168 other buyable models tracked here.

Count Tokens

Tokens

—

Input Cost

—

Output Cost

—

Tokens

—

Input Cost

—

Output Cost

Estimate Monthly Cost

Monthly Cost Estimator

Quick:

API calls / dayAvg input tokens / callAvg output tokens / call

<$0.0001/mo

Pick a preset above or enter custom usage

What GPT-OSS 120B Costs Per Request

At $0.039 per 1M input and $0.190 per 1M output tokens, before caching or batch discounts.

Workload	Input / output tokens	Per request	Per 10,000 requests
Chat reply	1,500 / 400	$0.0001	$1.34
RAG answer over retrieved docs	8,000 / 600	$0.0004	$4.26
Coding-agent step	30,000 / 2,000	$0.0015	$15.50

GPT-OSS 120B vs Similarly Priced Models

Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.

Model	Input /1M	Output /1M	Context	RAG answer
GPT-OSS 120B OpenAI	$0.039	$0.190	131K	$0.0004
GPT-OSS 20B (Bedrock) OpenAI	$0.070	$0.300	16K	$0.0007
Ling-3.0-flash Ant Group	$0.060	$0.180	262K	$0.0006
Qwen3.5-9B Alibaba	$0.100	$0.150	262K	$0.0009

Alternatives to GPT-OSS 120B

Cheaper Alternative

Mercury 2.5 (Preview)

$0.040 in · $0.150 out · Inception Labs

17% cheaper with same or larger context

Premium Upgrade

Ling-3.0-flash

$0.060 in · $0.180 out · Ant Group

Upgrade with 262K context

Same Provider

GPT-OSS 20B (Bedrock)

$0.070 in · $0.300 out · OpenAI

Higher tier in OpenAI ecosystem

Pricing Details

OpenAIOpenAI publishes NO rate for this model. It ships the weights (Apache 2.0) but sells no hosted inference for it, so the figure here is a third-party host's price, not OpenAI's, and it cannot be checked against an OpenAI page. Confirmed absent from OpenAI's own rate card on 2026-08-17. Open-weights models legitimately price differently on every host; treat this as one host's number.

Input / 1M tokens

$0.039

Output / 1M tokens

$0.19

Context Window

131K

Max Output

33K

Unverified rate. OpenAI has not published a price for GPT-OSS 120B. Treat these figures as indicative and confirm with OpenAI before relying on them.

Full Pricing Table Token Calculator

Price History

No price change recorded since 2026-08-11, when this site started tracking this model; it launched on 2025-08-05.

Frequently Asked Questions

Common questions about GPT-OSS 120B pricing and usage

How much does GPT-OSS 120B cost?

GPT-OSS 120B costs $0.039 per 1 million input tokens and $0.19 per 1 million output tokens. This pricing is set by OpenAI.

What tokenizer does GPT-OSS 120B use?

GPT-OSS 120B uses the o200k_base tokenizer. This is OpenAI's latest tokenizer, optimized for efficiency with a vocabulary of ~200,000 tokens.

What is GPT-OSS 120B's context window?

GPT-OSS 120B supports a context window of 131K tokens (131,072 tokens). The maximum output length is 33K tokens.

How does GPT-OSS 120B compare to other models?

On an 8,000-token-in, 600-token-out RAG answer, GPT-OSS 120B costs $0.0004 per request. The nearest-priced alternatives cost: GPT-OSS 20B (Bedrock) (OpenAI) $0.0007, Ling-3.0-flash (Ant Group) $0.0006, Qwen3.5-9B (Alibaba) $0.0009. The table above lists their full rates and context windows.

How do I count tokens for GPT-OSS 120B?

Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for GPT-OSS 120B using the o200k_base tokenizer.