Question 1

What is Qwen2.5 72B Instruct?

Accepted Answer

Qwen2.5 72B Instruct is a model from Qwen, released on Sep 19, 2024. **This repo contains the instruction-tuned 72B Qwen2.5 model**, which has the following features:.

Question 2

How much does Qwen2.5 72B Instruct cost?

Accepted Answer

On the Respan gateway, input starts at $0.34 per 1M tokens on Novita, and output starts at $0.36 per 1M tokens on Novita, after gateway discounts. Averaged across 5 providers, it costs $0.53 per 1M input tokens and $0.55 per 1M output tokens.

Question 3

Which providers serve Qwen2.5 72B Instruct on Respan?

Accepted Answer

5 providers serve Qwen2.5 72B Instruct: Novita, OpenRouter, DeepInfra, Featherless, and TogetherAI. TogetherAI requires your own provider API key (BYOK).

Question 4

What is Qwen2.5 72B Instruct's context window?

Accepted Answer

Qwen2.5 72B Instruct accepts up to 33K tokens of context on its largest provider route.

Question 5

How do I use Qwen2.5 72B Instruct with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "qwen2.5-72b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Qwen2.5 72B Instruct?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Novita at 10 tokens per second, and the lowest response latency was 4.2 seconds on Featherless. Speed varies with request size and provider.

Provider	Context	Input	Output
NovitaSave 10%`novita/qwen/qwen-2.5-72b-instruct`	32K	$0.34/M	$0.36/M
OpenRouter`openrouter/qwen/qwen-2.5-72b-instruct`	33K	$0.36/M	$0.40/M
DeepInfra`deepinfra/Qwen/Qwen2.5-72B-Instruct`	33K	$0.36/M	$0.40/M
Featherless`featherless_ai/Qwen/Qwen2.5-72B-Instruct`	33K	$0.37/M	$0.40/M
TogetherAIBYOK only`together_ai/Qwen/Qwen2.5-72B-Instruct`	33K	$1.20/M	$1.20/M

Qwen2.5 72B Instruct

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps