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: Claude Sonnet 4.5 (latest) ×

Model	Provider	Your cost/mo, $	Input, $	Output, $	Context
Anthropic: Claude Sonnet 4.5 (batch)	openrouter	$3.00	$1.50	$7.50	1M
Claude Sonnet 4.5 (Batch)	vercel	$3.00	$1.50	$7.50	1M
Claude Sonnet 4.5 (latest)	cometapi	$4.80	$2.40	$12.00	—
Claude-Sonnet-4.5	meganova	$4.80	$2.40	$12.00	1M
Claude Sonnet 4.5 (latest)	poe	$5.15	$2.58	$12.88	197K
claude-sonnet-4-5-20250929	jiekou	$5.70	$2.85	$14.25	200K
Claude Sonnet 4.5 (latest)	cortecs	$6.00	$3.00	$15.00	200K
Claude Sonnet 4.5 (latest)	edenai via Databricks	$6.00	$3.00	$15.00	200K
Claude Sonnet 4.5 (latest)	edenai via Databricks	$6.00	$3.00	$15.00	200K
Claude Sonnet 4.5	abacus	$6.00	$3.00	$15.00	200K
Claude Sonnet 4.5 (latest)	aiml	$6.00	$3.00	$15.00	—
Claude Sonnet 4.5	amazon-bedrock	$6.00	$3.00	$15.00	200K
Claude Sonnet 4.5 (Global)	amazon-bedrock	$6.00	$3.00	$15.00	200K
Claude Sonnet 4.5	anthropic	$6.00	$3.00	$15.00	200K
Claude Sonnet 4.5	azure	$6.00	$3.00	$15.00	200K
Claude Sonnet 4.5 (latest)	digitalocean	$6.00	$3.00	$15.00	—
Claude Sonnet 4.5 (latest)	edenai via Anthropic	$6.00	$3.00	$15.00	1M
Anthropic: Claude Sonnet 4.5	fastrouter	$6.00	$3.00	$15.00	200K
Claude Sonnet 4.5	google-vertex	$6.00	$3.00	$15.00	200K
Anthropic: Claude Sonnet 4.5	helicone	$6.00	$3.00	$15.00	200K

All 41 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.