Qwen 2.5 72B Instruct vs GPT-3.5 Turbo 16k: API price and specs

Qwen 2.5 72B Instruct is 92% cheaper than OpenAI: GPT-3.5 Turbo 16k on input price.

Qwen 2.5 72B Instruct is 90% cheaper than OpenAI: GPT-3.5 Turbo 16k on output price.

Qwen 2.5 72B Instruct is 92% cheaper than OpenAI: GPT-3.5 Turbo 16k on a 1M-in / 200k-out workload.

Qwen 2.5 72B Instruct has a 700% larger context than OpenAI: GPT-3.5 Turbo 16k.

Field	Qwen 2.5 72B Instruct	OpenAI: GPT-3.5 Turbo 16k
Lowest input, per 1M	$0.23	$3.00 +1204.3%
Median input, per 1M	$0.36	$3.00 +733.3%
Lowest output, per 1M	$0.40	$4.00 +900%
Median output, per 1M	$0.40	$4.00 +900%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.31	$3.80 +1125.8%
Context	131K	16K +87.5%
Max output	16K	4K +75%
Providers	11	5 +54.5%
Regions	US	US
Accepts	text	pdf, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	requesty	aihubmix

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, edenai, fastrouter, kilo, openrouter

Frequently asked questions

Which is cheaper, Qwen 2.5 72B Instruct or OpenAI: GPT-3.5 Turbo 16k?

Qwen 2.5 72B Instruct is 92% cheaper than OpenAI: GPT-3.5 Turbo 16k on input price. Qwen 2.5 72B Instruct is 90% cheaper than OpenAI: GPT-3.5 Turbo 16k on output price. Qwen 2.5 72B Instruct is 92% cheaper than OpenAI: GPT-3.5 Turbo 16k on a 1M-in / 200k-out workload.

Which has the larger context, Qwen 2.5 72B Instruct or OpenAI: GPT-3.5 Turbo 16k?

Qwen 2.5 72B Instruct: 131K tokens; OpenAI: GPT-3.5 Turbo 16k: 16K tokens.

Where can I use both Qwen 2.5 72B Instruct and OpenAI: GPT-3.5 Turbo 16k?

aihubmix, edenai, fastrouter, kilo, openrouter