gpt-oss-120b
OpenAIAn open-weight 120B model released by OpenAI under an open license, rather than an API-only model.
Main uses: Self-hosted or fine-tuned deployments where running your own weights matters more than using the latest closed model.
What sets it apart: Text-only, but at $0.037/$0.17 per 1M tokens it is far cheaper than any closed OpenAI model on this page.
On cost: Hosted via third-party providers here, not directly by OpenAI - compare routes before picking one.
In
$0.02
Out
$0.09
Blended
$0.04
Where to buy this model
24 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| ● PrimeIntellect cheapestfp4 | $0.02 | $0.09 | $0.04 | - |
| ● Near AI fp4 | $0.03 | $0.15 | $0.06 | +50% |
| ● Venice int4 | $0.03 | $0.15 | $0.06 | +50% |
| ● CoreWeave fp4 | $0.03 | $0.17 | $0.07 | +75% |
| ● DekaLLM bf16 | $0.03 | $0.18 | $0.07 | +75% |
| ● AkashML bf16 | $0.03 | $0.19 | $0.07 | +75% |
| $0.04 | $0.17 | $0.07 | +75% | |
| ● Crusoe bf16 | $0.05 | $0.25 | $0.10 | +150% |
| $0.05 | $0.25 | $0.10 | +150% | |
| ● Mancer 2 fp8 | $0.06 | $0.25 | $0.10 | +150% |
| ● Sail Research fp4 | $0.06 | $0.40 | $0.15 | +275% |
| $0.06 | $0.42 | $0.15 | +275% | |
| $0.09 | $0.36 | $0.16 | +300% | |
| $0.10 | $0.50 | $0.20 | +400% | |
 Amazon Bedrock | $0.15 | $0.60 | $0.26 | +550% |
| $0.15 | $0.60 | $0.26 | +550% | |
| ● SiliconFlow fp8 | $0.15 | $0.60 | $0.26 | +550% |
| ● Phala | $0.15 | $0.60 | $0.26 | +550% |
| $0.15 | $0.60 | $0.26 | +550% | |
| $0.15 | $0.60 | $0.26 | +550% | |
| $0.10 | $0.75 | $0.26 | +550% | |
| ● Mara | $0.15 | $0.75 | $0.30 | +650% |
| $0.14 | $0.95 | $0.34 | +750% | |
| $0.35 | $0.75 | $0.45 | +1025% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 131K
- max output
- 66K
- cache read /1M
- $0.02
- Family
- gpt
- Modalities
- text
- Features
- json · reasoning · tools
Live pricing, updated 2026-11-03.
OpenAI models at a similar price
| Model | In | Out | Ctx |
|---|---|---|---|
| gpt-oss-120b · this model | $0.024 | $0.087 | 131K |
| gpt-oss-20b | $0.03 | $0.13 | 131K |
| gpt-oss-safeguard-20b | $0.075 | $0.3 | 131K |
| GPT-5 Nano | $0.05 | $0.4 | 400K |
| GPT-4.1 Nano | $0.1 | $0.4 | 1.047576M |
| GPT-6 Luna | $0.1 | $0.5 | 1.05M |