AI Rate CardGPT-3.5 Turbo Instruct vs GPT-4 Turbo: API price and specs
GPT-3.5 Turbo Instruct is 72% cheaper than GPT-4 Turbo on input price.
GPT-3.5 Turbo Instruct is 88% cheaper than GPT-4 Turbo on output price.
GPT-3.5 Turbo Instruct is 78% cheaper than GPT-4 Turbo on a 1M-in / 200k-out workload.
GPT-4 Turbo has a 3025% larger context than GPT-3.5 Turbo Instruct.
| Field | GPT-3.5 Turbo Instruct | GPT-4 Turbo |
|---|---|---|
| Lowest input, per 1M | $1.40 | $5.00 +257.1% |
| Median input, per 1M | $1.50 | $10.00 +566.7% |
| Lowest output, per 1M | $1.80 | $15.00 +733.3% |
| Median output, per 1M | $2.00 | $30.00 +1400% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $1.76 | $8.00 +354.5% |
| Context | 4K +96.8% | 128K |
| Max output | 4K | 4K |
| Providers | 6 +50% | 12 |
| Regions | — | US |
| Accepts | image, pdf, text | file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | poe | openrouter |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
aihubmix, azure, kilo, openai, openrouter, poe
Frequently asked questions
Which is cheaper, GPT-3.5 Turbo Instruct or GPT-4 Turbo?
GPT-3.5 Turbo Instruct is 72% cheaper than GPT-4 Turbo on input price. GPT-3.5 Turbo Instruct is 88% cheaper than GPT-4 Turbo on output price. GPT-3.5 Turbo Instruct is 78% cheaper than GPT-4 Turbo on a 1M-in / 200k-out workload.
Which has the larger context, GPT-3.5 Turbo Instruct or GPT-4 Turbo?
GPT-3.5 Turbo Instruct: 4K tokens; GPT-4 Turbo: 128K tokens.
Where can I use both GPT-3.5 Turbo Instruct and GPT-4 Turbo?
aihubmix, azure, kilo, openai, openrouter, poe