Model tracker / OpenAI
gpt-oss-120b
gpt-oss-120b is a fast open-weight model from OpenAI, released 5 August 2025. At Novita AI it costs $0.05 per million input tokens and $0.25 per million output tokens, with a 131K-token context window. 13 providers serve it, and Novita AI is the cheapest.
- Made by
- OpenAI
- Released
- 2025-08-05
- Status
- Generally available
- Tier
- Fast
- Weights
- Open
- Context window
- 131,072 tokens
- Max output
- 32,768 tokens
- Input
- text
- API id
openai/gpt-oss-120b
gpt-oss-120b price at 13 providers
US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on. The cheapest blended price is highlighted.
| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| Novita AI | $0.05 | $0.25 | – | $0.10 | 50% off | 2026-10-14 |
| Google · gpt-oss-120b-maas | $0.09 | $0.36 | – | $0.158 | 50% off | 2026-10-14 |
| Baseten | $0.10 | $0.50 | – | $0.20 | – | 2026-10-14 |
| AWS · openai.gpt-oss-120b-1:0 | $0.15 | $0.60 | – | $0.262 | 50% off | 2026-10-14 |
| Fireworks AI · accounts/fireworks/models/gpt-oss-120b | $0.15 | $0.60 | $0.015 | $0.262 | 50% off | 2026-10-14 |
| Groq | $0.15 | $0.60 | $0.075 | $0.262 | 50% off | 2026-10-14 |
| Microsoft · gpt-oss-120b | $0.15 | $0.60 | – | $0.262 | – | 2026-10-14 |
| Nebius Group N.V. | $0.15 | $0.60 | – | $0.262 | – | 2026-10-14 |
| Together AI | $0.15 | $0.60 | – | $0.262 | – | 2026-10-14 |
| SambaNova · gpt-oss-120b | $0.22 | $0.59 | – | $0.313 | – | 2026-10-14 |
| Replicate | $0.18 | $0.72 | – | $0.315 | – | 2026-10-14 |
| Cerebras Systems · gpt-oss-120b | $0.35 | $0.75 | – | $0.45 | – | 2026-10-14 |
| Cloudflare · @cf/openai/gpt-oss-120b | $0.35 | $0.75 | – | $0.45 | – | 2026-10-14 |
- Novita AI: Batch inference at an introductory 50% discount; Novita's model data lists a batch endpoint for this model.
- Google: Vertex AI.
- AWS: Amazon Bedrock, US East (N. Virginia), Standard tier. Flex and Batch 50% off; Priority $0.2625 / $1.05.
- Fireworks AI: Priority tier: $0.18 / $0.72.
- Microsoft: Azure AI Foundry (open-source models section).
- Nebius Group N.V.: No cached-input or batch price published.
- Cerebras Systems: Pay-as-you-go developer tier.
- Cloudflare: Billed in Neurons at $0.011 per 1,000; 10,000 Neurons a day free.
Models like gpt-oss-120b
Other fast models closest in price, at each maker's own price or the cheapest provider.
| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| gpt-oss-120b | $0.05 | $0.25 | 131K | Open |
| Ministral 3 3B Mistral AI | $0.10 | $0.10 | 256K | Open |
| Qwen3.5 9B Alibaba | $0.10 | $0.15 | 262K | Open |
| gpt-oss-20b OpenAI | $0.07 | $0.25 | 131K | Open |
| NVIDIA Nemotron 3.5 Lightning 30B A3B NVIDIA | $0.06 | $0.16 | 262K | Open |
| Ministral 3 8B Mistral AI | $0.15 | $0.15 | 256K | Open |
Compare them all in the model tracker →
gpt-oss-120b on dbggr
- Aleph Alpha Kolibri: benchmarks, hardware and how to run it Article, 2026-10-07
gpt-oss-120b FAQ
How much does gpt-oss-120b cost?
gpt-oss-120b costs $0.05 per million input tokens and $0.25 per million output tokens at Novita AI, with 50% off for batch requests. Prices are list prices in US dollars, last checked 14 October 2026.
What is gpt-oss-120b's context window?
gpt-oss-120b takes up to 131,072 tokens in one request and writes up to 32,768 tokens in one response.
Is gpt-oss-120b open weight?
Yes. OpenAI publishes the weights, so you can run gpt-oss-120b yourself or at any host that serves it.
Where can I use gpt-oss-120b?
gpt-oss-120b is available from Novita AI, Google, Baseten, AWS, Fireworks AI, Groq, Microsoft, Nebius Group N.V., Together AI, SambaNova, Replicate, Cerebras Systems and Cloudflare. At Novita AI, call it as openai/gpt-oss-120b.