AI Rate CardGPT-3.5 Turbo 1106 vs GPT-4 Turbo: API price and specs
GPT-3.5 Turbo 1106 is 80% cheaper than GPT-4 Turbo on input price.
GPT-3.5 Turbo 1106 is 87% cheaper than GPT-4 Turbo on output price.
GPT-3.5 Turbo 1106 is 82% cheaper than GPT-4 Turbo on a 1M-in / 200k-out workload.
GPT-4 Turbo has a 681.2% larger context than GPT-3.5 Turbo 1106.
| Field | GPT-3.5 Turbo 1106 | GPT-4 Turbo |
|---|---|---|
| Lowest input, per 1M | $1.00 | $5.00 +400% |
| Median input, per 1M | $1.00 | $10.00 +900% |
| Lowest output, per 1M | $2.00 | $15.00 +650% |
| Median output, per 1M | $2.00 | $30.00 +1400% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $1.40 | $8.00 +471.4% |
| Context | 16K +87.2% | 128K |
| Max output | 4K | 4K |
| Providers | 4 +66.7% | 12 |
| Regions | — | US |
| Accepts | 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 | aihubmix | 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, fastrouter, openai
Frequently asked questions
Which is cheaper, GPT-3.5 Turbo 1106 or GPT-4 Turbo?
GPT-3.5 Turbo 1106 is 80% cheaper than GPT-4 Turbo on input price. GPT-3.5 Turbo 1106 is 87% cheaper than GPT-4 Turbo on output price. GPT-3.5 Turbo 1106 is 82% cheaper than GPT-4 Turbo on a 1M-in / 200k-out workload.
Which has the larger context, GPT-3.5 Turbo 1106 or GPT-4 Turbo?
GPT-3.5 Turbo 1106: 16K tokens; GPT-4 Turbo: 128K tokens.
Where can I use both GPT-3.5 Turbo 1106 and GPT-4 Turbo?
aihubmix, azure, fastrouter, openai