GPT-3.5 Turbo (older v0613) vs GPT Mini Latest
GPT-3.5 Turbo (older v0613) (OpenAI) and GPT Mini Latest (OpenAI) are listed at different prices. GPT Mini Latest costs less for input, $0.75 per 1M tokens against $1.00; GPT-3.5 Turbo (older v0613) costs less for output, $2.00 per 1M tokens against $4.50. GPT Mini Latest has the larger context window, 400,000 tokens against 4,095 for GPT-3.5 Turbo (older v0613). Only GPT Mini Latest supports a reasoning effort setting. GPT-3.5 Turbo (older v0613) accepts text and produces text; GPT Mini Latest accepts text, images and files and produces text.
GPT-3.5 Turbo (older v0613) accepts and produces text, with a 4,095-token context; GPT Mini Latest accepts text, images, and files and has a 400,000-token context. Both produce text and support tools, structured outputs, and response formats; GPT Mini Latest also lists reasoning support.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | GPT-3.5 Turbo (older v0613) | GPT Mini Latest |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Added to catalog | 25 Jan 2024 | 27 Apr 2026 |
| Input, per 1M tokens | $1.00 | $0.75 |
| Output, per 1M tokens | $2.00 | $4.50 |
| Cached input read, per 1M | n/a | $0.075 |
| Context windowTokens | 4,095 | 400,000 |
| Max outputTokens | 3,685 | 128,000 |
| Accepts | text | file, image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | GPT-3.5 Turbo (older v0613) | GPT Mini Latest |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0011 | $0.0017 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.027 | $0.022 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.034 | $0.032 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.153 | $0.119 |
Which to choose
Choose GPT-3.5 Turbo (older v0613) if
- Output tokens cost less: $2.00 against $4.50 per 1M
Choose GPT Mini Latest if
- Input tokens cost less: $0.75 against $1.00 per 1M
- Cached input costs less: $0.075 against n/a per 1M
- You need the larger context window: 400,000 tokens against 4,095
- You need longer answers in one response: 128,000 tokens against 3,685
- It has to read images and files, which the other model does not
- You want to set how much it reasons before it answers
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.