gpt-oss-20b pricing.
Prices checked
gpt-oss-20b costs $0.02 in and $0.09 out per million tokens from OpenRouter; the cheapest price is $0.02 at TrustedRouter, checked .
OpenRouter's own price
OpenRouter
$0.02 in · $0.09 out
96% below the typical price of the 392 text models we track.
Cheapest price
TrustedRouter
$0.01 in · $0.05 out
46% less than OpenRouter, and the provider says why.
Every provider selling gpt-oss-20b
- 1
$0.01 in · $0.05 out
$0.02/M tokens - 2
$0.02 in · $0.09 out
$0.04/M tokens - 3
$0.02 in · $0.09 out
$0.04/M tokens - 4
Darkbloom
Same as maker$0.02 in · $0.09 out
$0.04/M tokens - 5
$0.02 in · $0.09 out
$0.04/M tokens - 6
$0.02 in · $0.10 out
$0.04/M tokens - 7
AkashML
Costs more$0.02 in · $0.10 out
$0.04/M tokens - 8
CoreWeave
Costs more$0.03 in · $0.13 out
$0.06/M tokens - 9
CoreWeave
Costs more$0.03 in · $0.13 out
$0.06/M tokens - 10
DekaLLM
Costs more$0.03 in · $0.14 out
$0.06/M tokens - 11
$0.03 in · $0.14 out
$0.06/M tokens - 12
$0.03 in · $0.14 out
$0.06/M tokens - 13
$0.03 in · $0.14 out
$0.06/M tokens - 14
$0.03 in · $0.14 out
$0.06/M tokens - 15
$0.03 in · $0.14 out
$0.06/M tokens - 16
$0.03 in · $0.15 out
$0.06/M tokens - 17
$0.04 in · $0.15 out · 128k context here
$0.07/M tokens - 18
$0.04 in · $0.15 out
$0.07/M tokens - 19
$0.04 in · $0.18 out
$0.07/M tokens - 20
$0.04 in · $0.18 out
$0.07/M tokens - 21
$0.04 in · $0.17 out
$0.08/M tokens - 22
$0.04 in · $0.19 out
$0.08/M tokens - 23
Clarifai
Costs more$0.04 in · $0.18 out
$0.08/M tokens - 24
$0.05 in · $0.17 out · 64k context here
$0.08/M tokens - 25
$0.05 in · $0.18 out
$0.08/M tokens
- 26
$0.05 in · $0.20 out
$0.09/M tokens - 27
$0.05 in · $0.20 out
$0.09/M tokens - 28
$0.05 in · $0.20 out
$0.09/M tokens - 29
$0.05 in · $0.20 out
$0.09/M tokens - 30
$0.07 in · $0.15 out
$0.09/M tokens - 31
FrogBot
Costs more$0.07 in · $0.20 out
$0.10/M tokens - 32
$0.07 in · $0.25 out
$0.12/M tokens - 33
$0.07 in · $0.25 out · 128k context here
$0.12/M tokens - 34Costs more
$0.07 in · $0.30 out
$0.13/M tokens - 35
$0.07 in · $0.30 out
$0.13/M tokens - 36
$0.07 in · $0.30 out
$0.13/M tokens - 37
$0.07 in · $0.30 out
$0.13/M tokens - 38
$0.07 in · $0.30 out
$0.13/M tokens - 39Costs more
$0.07 in · $0.30 out
$0.13/M tokens - 40
$0.07 in · $0.30 out
$0.13/M tokens - 41Costs more
$0.08 in · $0.32 out
$0.14/M tokens - 42
$0.10 in · $0.50 out
$0.20/M tokens - 43
Regolo AI
Costs more$0.11 in · $0.47 out · 128k context here
$0.20/M tokens - 44
LowRouter
Costs more$0.11 in · $0.47 out
$0.20/M tokens - 45
STACKIT
Costs more$0.18 in · $0.29 out
$0.21/M tokens - 46
$0.12 in · $0.49 out · 128k context here
$0.21/M tokens - 47
$0.20 in · $0.30 out · 128k context here
$0.23/M tokens - 48
Thinking Machines
Costs more$0.18 in · $0.45 out · 33k context here
$0.25/M tokens
Not ranked
Below the maker's own price with nothing published to account for it, from a catalog we could not read reliably, or a free tier, which is a limit rather than a price. Why
QVAC
Free tiergiven away with limits
freegiven away with limits
free$0.04 in · $0.15 out
$0.07/M tokens$0.06 in · $0.27 out
$0.11/M tokens
What it costs for your work
A month at OpenRouter's own price
A month at TrustedRouter, the cheapest
What you save
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
Run it yourself
On a server by the month
OpenAI publishes the weights, so you can run gpt-oss-20b on a server you rent by the month. It needs about 14 GB of RAM on a CPU, and the cheapest plan we track with that much and a disk included is Leaseweb VPS 3 at $14.07 a month, streaming about 4.4–8.7 tok/s. Every plan that fits
On a GPU by the hour
The RTX A5000 holds gpt-oss-20b in 24 GB of memory against the 14 GB the weights, the context and the runtime need. The cheapest one we track is RunPod's RTX A5000 · Community Cloud at $0.16/GPU-hr, which is $116.80 for the 730 hours in a month, checked 31 Oct. Every GPU price
How we count
Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below OpenRouter's own is listed as cheapest only when the provider says why. OpenAI trained gpt-oss-20b and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.
- Resells
- The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Same as maker
- Sold by someone else at the price the maker charges.
- Costs more
- Sold by someone else for more than the maker charges.
- Free tier
- Given away inside a quota. A limit is not a price, so it is never called cheapest.
- Not ranked
- Below the maker's price on a closed model with nothing to account for it, or from a catalog we could not read reliably. Listed, and never a pick.
Similar models
Models from other labs that do what gpt-oss-20b does, cheapest first. Each percentage is against gpt-oss-20b's cheapest price, $0.02 per M tokens.
Frequently asked
- Who sells gpt-oss-20b cheapest?
- TrustedRouter, at $0.01 in and $0.05 out per million tokens, checked 31 Oct 2026. The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Is gpt-oss-20b open weights?
- Yes. OpenAI publishes the weights, so anyone may host gpt-oss-20b, which is why 47 providers sell it and why their prices differ so much.
- How much context does gpt-oss-20b hold?
- 131,072 tokens in one call, which is about 131k, and it can call your own functions.
- How does gpt-oss-20b compare with the rest of the market?
- At $0.04 per million tokens, OpenRouter's own price is 96% below the typical $0.88 across the 392 text models we track.
More from OpenAI