GPT-OSS 20B API Pricing — $0.07/M input, $0.30/M output
Compact open-weight MoE model.
Speed
Tokens / sec
1120
TTFT
140 ms
Rank
#3 of 31
$ / M ÷ t/s
$0.0001
Measured with 5 runs on a fixed prompt — see the full methodology.
Cost at scale
| Tokens / month | Est. cost (blended 3:1) |
|---|---|
| 100,000 | $0.01 |
| 1,000,000 | $0.13 |
| 10,000,000 | $1.31 |
| 100,000,000 | $13.12 |
How GPT-OSS 20B compares
Llama 3.1 8B — $0.06/MGPT-OSS 120B — $0.26/MLlama 4 Maverick — $0.30/MLlama 3.3 70B — $0.64/MQwen 3.8 30B — $1.20/MGPT-5 Nano — $0.14/MMinistral 8B — $0.15/MAmazon Nova Lite — $0.11/M
FAQ
Is GPT-OSS 20B cheaper than GPT-5 Nano?
GPT-OSS 20B costs $0.13/M blended tokens, GPT-5 Nano costs $0.14/M — GPT-OSS 20B is cheaper.
How much does 1 million tokens cost with GPT-OSS 20B?
At a 3:1 input:output ratio, 1 million blended tokens costs approximately $0.13. Pure input costs $0.07/M; pure output costs $0.30/M.
Who provides GPT-OSS 20B?
GPT-OSS 20B is served by Groq. Pricing was last verified on 2026-04-06 against https://console.groq.com/docs/models.
