Skip to content
CostPerPrompt

gpt-oss-20b API Pricing

OpenAI · context window 131K · prices updated 2026-09-29

Input per 1M tokens
$0.018
Output per 1M tokens
$0.09
Cached input per 1M
$0.009
50% cheaper than fresh input

Where gpt-oss-20b sits on price

At $0.09 per million output tokens, gpt-oss-20b is a budget tier model — 24.4× cheaper than the median output price of $2.20, which puts it in the cheapest 10% of everything we track. It is the cheapest of the 100 OpenAI models we track. Output costs 5.0× input, the usual spread — trim both, starting with the answer length.

Output tokens per $1
11,111,111
One full context fill
$0.0024
Cheaper than
99% of tracked models

Cached input is 50% cheaper. On an input-heavy workload you need roughly a 50% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.

What real workloads cost on gpt-oss-20b

These three workloads are the ones teams actually run on a budget-priced model — a $0.09/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. $0 $54.00
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0 $0.675
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0001 $29.70

Model your exact traffic in the API cost calculator — it preloads gpt-oss-20b with caching and batch options.

gpt-oss-20b price history

OpenAI last cut gpt-oss-20b's output price on Sep 23, 2026 (-31% per output token), from $0.03/$0.13 to $0.018/$0.09 per 1M in/out. That is the only repricing in the 58 days we have tracked it — worth knowing before you hard-code today's rate into a budget.

Date Input /1M Output /1M Output change
Aug 2, 2026 (tracking began) $0.03 $0.13 —
Sep 23, 2026 $0.018 $0.09 -31%

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

gpt-oss-20b vs Llama 3.1 8B Instruct

The closest-priced alternative from another vendor is Llama 3.1 8B Instruct (Meta) — 11% cheaper on output, with $0.032 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Llama 3.1 8B Instruct pricing →

Cheaper alternatives

More OpenAI models

Frequently asked questions

› How much does the gpt-oss-20b API cost?

gpt-oss-20b costs $0.018 per million input tokens and $0.09 per million output tokens, with cached input at $0.009 per million (50% cheaper). That works out to roughly 11,111,111 output tokens per dollar.

› What does the high-volume classification workload cost on gpt-oss-20b?

High-volume classification — 200K requests/day (400 in / 20 out) costs about $0 per request and $54.00 per month on gpt-oss-20b. Short output, huge volume: the input price dominates the bill.

› What does it cost to fill gpt-oss-20b's 131K context window?

Sending 131K of input in a single request costs $0.0024 at $0.018 per million tokens — before any output. With prompt caching that same fill drops to about $0.0012 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

› Is gpt-oss-20b worth the price?

gpt-oss-20b is in the cheapest end of the market — cheaper than 99% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.