gpt-oss-120b
GPT OSS 120B
Made by OpenAI. Sold by 4 providers, from ≈$0.09 per million input tokens.
- Maker
- OpenAI
- Released
- 2025-08-05
- Context
- 131K tokens
- Max output
- 131K tokens
- Input
- text
- Output
- text
- Open weights
- Yes
- Knowledge cutoff
- 2024-10
Where to buy it
| Provider | Input $/M | Output $/M | Blended* | Holds your prompt | Training |
|---|---|---|---|---|---|
| OVHcloud | ≈$0.09 €0.08 | ≈$0.45 €0.40 | ≈$0.18 | runs it 🇫🇷 France | no training |
| Google Vertex AI | $0.09 | $0.36 | $0.16 | runs it 🇺🇸 United States | off by default |
| Amazon BedrockOpenAI-compatible API | $0.15 | $0.60 | $0.26 | runs it 🇺🇸 United States | no training |
| Amazon Bedrockruntime API | $0.15 | $0.60 | $0.26 | runs it 🇺🇸 United States | no training |
| nebius | $0.15 | $0.60 | $0.26 | runs it 🇳🇱 Netherlands | no training |
≈ converted from EUR at 1 EUR = $1.1193 (ECB reference rate, 2026-10-23)
Blended is our calculation: (3 × input + output) ÷ 4, US dollars per million tokens — most calls read far more than they write. Tiers that are cheaper because they train on your data are not used for the “from” price.