OpenAI GPT 120B
openai/gpt-oss-120b
Text
8 gateways
5x price spread
Where you can run it
| Gateway | Its id | Context | Max output | Input / Mtok | Output / Mtok |
|---|---|---|---|---|---|
| Baseten | openai/gpt-oss-120b |
128.1K | 128.1K | $0.100 | $0.500 |
| Cloudflare AI Gateway | openai/gpt-oss-120b |
— | — | — | — |
| Fireworks AI | accounts/fireworks/models/gpt-oss-120b |
131.1K | — | — | — |
| NanoGPT Cheapest input | openai/gpt-oss-120b |
128K | 16.4K | $0.030 | $0.150 |
| OpenRouter | openai/gpt-oss-120b |
131.1K | 65.5K | $0.150 | $0.600 |
| Requesty | sail/gpt-oss-120b |
131.1K | 131.1K | $0.060 | $0.400 |
| Together AI | openai/gpt-oss-120b |
131.1K | — | $0.150 | $0.600 |
| Vercel AI Gateway | openai/gpt-oss-120b |
131.1K | 131.1K | $0.100 | $0.500 |
Prices are US dollars per million tokens, as published in each gateway's own catalog at the last crawl. A dash means that gateway publishes no value — not that it is free. Rows differ because gateways set their own markup, and some let you bring your own provider key.
- Canonical id
openai/gpt-oss-120b- Vendor
- OpenAI
- Type
- Text
- Gateways serving it
- BasetenCloudflareFireworksNanoGPTOpenRouterRequestyTogetherVercel
- Batch pricing
- openai/gpt-oss-120b:batch
- Largest context window
- 131.1K tokens
- Input price range
- $0.030 – $0.150 / Mtok
- Price spread
- 5x between cheapest and dearest gateway
- Accepts
- Text
- Returns
- Text
- Cataloged since
History
What changed for OpenAI GPT 120B
Recorded by the daily catalog crawl — when gateways picked this model up, dropped it, or repriced it.
- Experiential Labs added gpt-oss-120b
- Cheaper Inference added gpt-oss-120b
- LLM Gateway added GPT OSS 120B
- Concentrate added OpenAI gpt-oss 120B
- Ramp Router added OpenAI gpt-oss-120b
- OpenRouter raised input 733.3% to $0.150 and output 795.5% to $0.600 on OpenAI: gpt-oss-120b
- Experiential Labs added gpt-oss-120b
- Cheaper Inference added gpt-oss-120b
- LLM Gateway added GPT OSS 120B
- Concentrate added OpenAI gpt-oss 120B
- Ramp Router added OpenAI gpt-oss-120b
- OpenRouter cut input 88% to $0.018 and output 88.8% to $0.067 on OpenAI: gpt-oss-120b
- Experiential Labs added gpt-oss-120b
- Cheaper Inference added gpt-oss-120b