Tools: pick a model by cost

Find the cheapest offer for your monthly workload, count the tokens of a prompt, convert price units.

Cost picker

How many tokens a month you send to the model (input) and get back (output), in millions. For example, a chatbot with 1,000 conversations a day is about 10 M input and 2 M output. Don't know your numbers? Count them below in the token estimator.

Model: Qwen3-Next 80B-A3B Instruct ×

Model	Provider	Your cost/mo, $	Input, $	Output, $	Context
Qwen3 Next 80B A3B Instruct	qiniu-ai	$0.26	$0.14	$0.58	131K
Qwen3-Next 80B-A3B Instruct	deepinfra	$0.31	$0.09	$1.10	262K
Qwen3-Next 80B-A3B Instruct	edenai via DeepInfra	$0.31	$0.09	$1.10	262K
Qwen: Qwen3 Next 80B A3B Instruct	fastrouter	$0.31	$0.09	$1.10	262K
Qwen3-Next-80B-A3B-Instruct	huggingface	$0.31	$0.09	$1.10	262K
Qwen: Qwen3 Next 80B A3B Instruct	kilo	$0.32	$0.10	$1.10	262K
Qwen: Qwen3 Next 80B A3B Instruct	openrouter	$0.32	$0.10	$1.10	262K
Qwen: Qwen3 Next 80B A3B Instruct	trustedrouter	$0.33	$0.09495	$1.16	262K
Qwen: Qwen3 Next 80B A3B Instruct	io-net	$0.34	$0.09925	$1.18	262K
Qwen3-Next 80B-A3B Instruct	google-vertex	$0.39	$0.15	$1.20	—
Qwen3 Next 80B A3B Instruct	vercel	$0.39	$0.15	$1.20	262K
Qwen3-Next 80B-A3B Instruct	edenai via Databricks	$0.39	$0.15	$1.20	—
Qwen3-Next 80B-A3B Instruct	aiml	$0.41	$0.16	$1.27	—
Qwen3 Next 80B A3B Instruct	helicone	$0.42	$0.14	$1.40	262K
Qwen3-Next 80B-A3B Instruct	jiekou	$0.45	$0.15	$1.50	—
Qwen3-Next 80B-A3B Instruct	poe	$0.45	$0.15	$1.52	—
Qwen3-Next 80B-A3B Instruct	trustedrouter via Venice	$0.77	$0.37	$2.00	—
Qwen3-Next 80B-A3B Instruct	aihubmix	$0.25	$0.14	$0.55	—

All 18 in Models

Token estimator

Don't know your workload in tokens? Paste an example of your prompt, say how many such requests you make a month and how long an answer is: you get the monthly workload. The button puts it into the picker above and shows the offers.

Price units

Providers quote per token, per 1K or per 1M tokens: the same price in all three.

AI picker

Describe the task in your own words - what the model must do, how fast, the budget, the region - and get a short list of models and providers with the reasons.

Coming soon.