Two well-known open models that work differently. gpt-oss-120b reasons step by step and is far stronger at maths and science; Llama 3.3 70B answers straight away and is a steadier writer. On Roar AI, gpt-oss-120b costs $0.195 and Llama 3.3 70B costs $0.3809 per million input tokens.
| Feature | gpt-oss-120b | Llama 3.3 70B |
|---|---|---|
| Made by | OpenAI | Meta |
| Released | August 2025 | December 2024 |
| Input price, per 1M tokens | $0.195 | $0.3809 |
| Output price, per 1M tokens | $0.78 | $2.9289 |
| Cached input, per 1M tokens | $0.0975 | — |
| Batch (usually about half price) | No | No |
| Context window | 131K tokens | 128K tokens |
| Longest answer | 131K tokens | — |
| Reads | Text | Text |
| Thinks before answering | Always on | No |
| Open weights | Yes: Apache 2.0 | Yes: Llama 3.3 Community License |
Prices are Roar AI’s published rates, live from our price list. Specs are each lab’s own published figures.
Pick by whether the task needs thinking.
Take 1,000 requests, each about 3,000 tokens in and 1,000 out: a long prompt and a page of answer.
gpt-oss-120b is 3× cheaper for the same job. Models that think before answering spend extra output tokens doing it, so on hard prompts the gap can be wider than the rates suggest.
On Roar AI both are on the same key and the same monthly invoice. Trying the other one is a one-word change:
client.chat.completions.create(model="gpt-oss-120b", …) client.chat.completions.create(model="llama-3.3-70b", …)
Send the same prompts to both and compare the answers on your own work. Read the docs.
On Roar AI, gpt-oss-120b costs $0.195 per million input tokens and $0.78 per million output tokens, and Llama 3.3 70B costs $0.3809 per million input tokens and $2.9289 per million output tokens. For 1,000 requests of about 3,000 tokens in and 1,000 out, that is $1.36 and $4.07.
gpt-oss-120b reads up to 131K tokens at once, against 128K tokens for Llama 3.3 70B.
Yes. On Roar AI both models answer on the same OpenAI-compatible API, with one key and one monthly bill, so switching between them is a change to the model name.
Create a free account and call both models with one API key.