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 Opus 4.5 (latest) ×

Model	Provider	Your cost/mo, $	Input, $	Output, $	Context
Anthropic: Claude Opus 4.5 (batch)	openrouter	$5.00	$2.50	$12.50	200K
Claude Opus 4.5 (Batch)	vercel	$5.00	$2.50	$12.50	200K
Claude Opus 4.5 (latest)	cometapi	$8.00	$4.00	$20.00	—
Claude-Opus-4.5	meganova	$8.00	$4.00	$20.00	200K
Claude Opus 4.5 (latest)	poe	$8.59	$4.29	$21.46	197K
claude-opus-4-5-20251101	jiekou	$9.50	$4.75	$23.75	200K
claude-opus-4-5-20251101	302ai	$10.00	$5.00	$25.00	200K
Claude Opus 4.5	abacus	$10.00	$5.00	$25.00	200K
Claude Opus 4.5	aihubmix	$10.00	$5.00	$25.00	200K
Claude Opus 4.5 (latest)	aiml	$10.00	$5.00	$25.00	—
Claude Opus 4.5	amazon-bedrock	$10.00	$5.00	$25.00	200K
Claude Opus 4.5 (Global)	amazon-bedrock	$10.00	$5.00	$25.00	200K
Claude Opus 4.5	anthropic	$10.00	$5.00	$25.00	200K
Claude Opus 4.5	azure	$10.00	$5.00	$25.00	200K
Claude Opus 4.5 (latest)	digitalocean	$10.00	$5.00	$25.00	—
Claude Opus 4.5 (latest)	edenai via Anthropic	$10.00	$5.00	$25.00	200K
Claude Opus 4.5 (latest)	edenai via Google Vertex AI	$10.00	$5.00	$25.00	200K
Anthropic: Claude Opus 4.5	fastrouter	$10.00	$5.00	$25.00	200K
Claude Opus 4.5	google-vertex	$10.00	$5.00	$25.00	200K
Anthropic: Claude Opus 4.5	helicone	$10.00	$5.00	$25.00	200K

All 39 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.