SIDE BY SIDE
GPT-3.5 Turbo (older v0613) vs gpt-oss-120b
Both are GPT models. gpt-oss-120b was added to OpenRouter on 2025-08-05, GPT-3.5 Turbo (older v0613) on 2024-01-25.
| Field | GPT-3.5 Turbo (older v0613) | gpt-oss-120b |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Family | GPT | GPT |
| Province | Blossom Valley | Blossom Valley |
| Context window | 4K tokens | 131K tokens |
| Maximum output | 4K tokens | 66K tokens |
| Input / 1M tokens | $1.00 | $0.150 |
| Output / 1M tokens | $2.00 | $0.600 |
| Accepts | text | text |
| Produces | text | text |
| Reasoning | No | Yes |
| Tool use | Yes | Yes |
| Added to OpenRouter | 2024-01-25 | 2025-08-05 |
| Model ID | openai/gpt-3.5-turbo-0613 | openai/gpt-oss-120b |
Questions and answers
Which is cheaper, GPT-3.5 Turbo (older v0613) or gpt-oss-120b?
gpt-oss-120b costs less for both input ($0.150 vs $1.00) and output ($0.600 vs $2.00) per million tokens. On input, gpt-oss-120b is 85% cheaper.
Which has the larger context window?
gpt-oss-120b: 131K tokens against 4K for GPT-3.5 Turbo (older v0613) (32× as long).
What can one do that the other cannot?
Only gpt-oss-120b supports reasoning.
Answers are computed from the 2026-10-24 catalog snapshot.