AI Token Price
OpenAI

OpenAI · 2 current models

gpt-oss API pricing

OpenAI's open-weight models, released under Apache 2.0 in August 2025. Many hosts run them; prices here are the cheapest listed on OpenRouter.

gpt-oss-120b

Input
$0.15
per 1M tokens
Output
$0.60
per 1M tokens
Cached input
—
not published
Batch
—
no discount offered
Context window
128K
tokens
Verified 27 Sep 2026OpenRouter listing

What it costs in practice

gpt-oss-120b at list prices, no batch discount.

What gpt-oss-120b costs for three workloads
1,000 chat replies1,500 tokens in and 300 out each$0.41
Summarising 100 long reports20,000 tokens in and 800 out each$0.35
A month of a coding agent400 tasks, 85% of input cached$117

The coding-agent example assumes 85% of input is served from cache, typical for agents that resend the same context each step. Model your own workload

Details

API model IDgpt-oss-120b
Released5 Aug 2025
WeightsOpen (Apache 2.0), 117B total and 5.1B active parameters
StatusCurrent

Cheapest host listed on OpenRouter. Prices vary by host.

Checked 27 Sep 2026 against OpenRouter listing .

Other gpt-oss models

Because the weights are open, you can also run them yourself. See the local LLM calculator.

Other gpt-oss models and prices per million tokens
Model Input / 1M Output / 1M Cached input Context Released
Open weights · via OpenRouter
$0.018 $0.090 — 128K 5 Aug 2025

gpt-oss-20b details

gpt-oss-20b

$0.018 / $0.090 per 1M tokens128K context

Released 5 Aug 2025 · gpt-oss-20b

Cheapest host listed on OpenRouter. Prices vary by host.

Checked 27 Sep 2026 against OpenRouter listing .

Compare gpt-oss-120b

No ready-made comparisons for this family yet.

Compare with any model

Price history

All changes

No price changes recorded since we began tracking in June 2026.

OpenAI pricing rules

  • Batch and Flex processing cost 50% less.
  • For GPT-5.4 and later, prompts longer than 272K tokens are billed at 2× the input price and 1.5× the output price.
  • Cached input is billed at about a tenth of the input price.

All OpenAI models

Questions

How much does gpt-oss-120b cost?

As of 27 Sep 2026, gpt-oss-120b costs $0.15 per million input tokens and $0.60 per million output tokens. Prices checked 27 Sep 2026.

What is the cheapest gpt-oss model?

gpt-oss-20b, at $0.018 / $0.09 per million input / output tokens.

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

128K tokens.