Which is cheaper, gpt-oss-120b or Mercury 2.5?

gpt-oss-120b, at $0.24 per million tokens against $0.27 for Mercury 2.5, three parts input to one part output, read on 16 Sept 2026.

Where is each one cheapest?

gpt-oss-120b: $0.24 at LLM Gateway. Mercury 2.5: nobody goes below the maker's own price with a reason we can point at, so $0.27 is the number to beat.

Can I buy both from one provider?

Yes. 5 providers sell both: Nous Portal, OpenRouter, Vercel AI Gateway, Kilo Gateway, NanoGPT. The cheapest of them for the two together is Nous Portal.

Which holds more context?

Mercury 2.5, at 260k tokens against 131k.

gpt-oss-120b vs Mercury 2.5.

model vs model · prices as of 16 Sept 2026

Mercury 2.5 takes 3 of 5 rounds against gpt-oss-120b. gpt-oss-120b counters on price: $0.24 per million tokens against $0.27, for 131k context instead of 260k.

OpenAI

gpt-oss-120b

$0.24/M tokens

cheapest we can explain, at LLM Gateway · $0.0276 per 1,000 pages

131k context · tool calling · open weights

LLM Gateway ↗

Inceptionwins 3 rounds

Mercury 2.5

$0.27/M tokens

Inception list price, nothing below it is accounted for · $0.033 per 1,000 pages

260k context · tool calling

List price in (lower wins)

$0.04/M

List price out (lower wins)

$0.17/M

$0.15/M

Cheapest we can explain (lower wins)

$0.24/M at LLM Gateway

none below list

Standard price (lower wins)

$0.28/M

$0.27/M

Cost per 1,000 pages (lower wins)

$0.0276

$0.033

Context

131k tokens

260k tokens

Open weights

yes

Tool calling

yes

Structured output

yes

Reads images

Reasoning

yes

Released

5 Aug 2025

8 Sept 2026

Providers selling it

Price we measure against

OpenRouter

the maker's own

Trains on your prompts (no is better)

not stated

no provider to check

Providers selling both · 5

Nous Portal$0.26 / $0.27
OpenRouter$0.28 / $0.27
Vercel AI Gateway$0.80 / $0.27
Kilo Gateway$0.26 / $1.35
NanoGPT$8 / $0.12

gpt-oss-120b then Mercury 2.5, per million tokens

Go further

open in the compare tool →every price for gpt-oss-120b every price for Mercury 2.5

Add a third or fourth model, or switch the weighting, in the tool.

What moved in the last seven days

gpt-oss-120bCharm Hyper$0.17 / $0.66 $0.18 / $0.684% dearer · 16 Sept 2026
gpt-oss-120bDeepInfra$0.15 / $0.60 $0.04 / $0.1773% cheaper · 16 Sept 2026
gpt-oss-120bDigitalOcean Gradient$0.06 / $0.39 $0.06 / $0.429% dearer · 16 Sept 2026
gpt-oss-120bEden AI$0.17 / $0.76 $0.17 / $0.750.6% cheaper · 16 Sept 2026
gpt-oss-120bio.net Intelligence$0.17 / $0.66 $0.18 / $0.684% dearer · 16 Sept 2026
gpt-oss-120bMancer$22,000 / $200,000 $20,000 / $160,00017% cheaper · 16 Sept 2026
gpt-oss-120bMancer$0.06 / $0.50 $0.05 / $0.4017% cheaper · 16 Sept 2026
gpt-oss-120bNous Portal$0.02 / $0.14 $0.03 / $0.1725% dearer · 16 Sept 2026
gpt-oss-120bRequesty$0.15 / $0.60 $0.03 / $0.1478% cheaper · 16 Sept 2026
Mercury 2.5Nous Portal$0.03 / $0.12 $0.04 / $0.1525% dearer · 16 Sept 2026

Frequently asked

Which is cheaper, gpt-oss-120b or Mercury 2.5?: gpt-oss-120b, at $0.24 per million tokens against $0.27 for Mercury 2.5, three parts input to one part output, read on 16 Sept 2026.
Where is each one cheapest?: gpt-oss-120b: $0.24 at LLM Gateway. Mercury 2.5: nobody goes below the maker's own price with a reason we can point at, so $0.27 is the number to beat.
Can I buy both from one provider?: Yes. 5 providers sell both: Nous Portal, OpenRouter, Vercel AI Gateway, Kilo Gateway, NanoGPT. The cheapest of them for the two together is Nous Portal.
Which holds more context?: Mercury 2.5, at 260k tokens against 131k.

Prices exclude tax and are per million tokens, read 16 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.