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: DeepSeek V4 Flash 0731 ×

Model	Provider	Your cost/mo, $	Input, $	Output, $	Context
DeepSeek: DeepSeek V4 Flash 0731	trustedrouter	$0.06119	$0.0422	$0.09495	1M
DeepSeek V4 Flash 0731	deepinfra	$0.096	$0.06	$0.18	—
DeepSeek V4 Flash 0731	edenai via DeepInfra	$0.096	$0.06	$0.18	1M
DeepSeek V4 Flash 0731	huggingface	$0.096	$0.06	$0.18	1M
DeepSeek V4 Flash 0731	requesty via DeepInfra	$0.10	$0.072	$0.14	1M
DeepSeek V4 Flash 0731	ambient	$0.12	$0.08	$0.18	1M
DeepSeek: DeepSeek V4 Flash 0731	openrouter	$0.12	$0.059	$0.30	1M
DeepSeek-V4-Flash-0731	meganova	$0.13	$0.09	$0.18	1M
DeepSeek V4 Flash 0731	vultr	$0.15	$0.10	$0.25	1M
DeepSeek V4 Flash 0731	inferx	$0.15	$0.11	$0.22	—
DeepSeek V4 Flash 0731	cortecs	$0.17	$0.08272	$0.41	1M
DeepSeek V4 Flash 0731	edenai via FlexAI	$0.17	$0.12	$0.24	1M
DeepSeek V4 Flash 0731	edenai via FlexAI	$0.17	$0.12	$0.24	1M
DeepSeek V4 Flash 0731	melious	$0.17	$0.11	$0.28	—
DeepSeek V4 Flash 0731	wafer.ai	$0.18	$0.13	$0.23	1M
DeepSeek V4 Flash 0731	baseten	$0.18	$0.13	$0.26	—
DeepSeek V4 Flash 0731	perplexity-agent	$0.18	$0.13	$0.26	1M
DeepSeek V4 Flash 0731	vercel	$0.18	$0.13	$0.26	1M
DeepSeek V4 Flash 0731	runinfra	$0.18	$0.13	$0.27	1M
DeepSeek V4 Flash 0731 Fast	trustedrouter	$0.19	$0.14	$0.24	1M

All 50 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.