Claude Haiku 4.5 (latest) vs Sonar: API price and specs

Sonar is 50% cheaper than Claude Haiku 4.5 (latest) on input price.

Sonar is 60% cheaper than Claude Haiku 4.5 (latest) on output price.

Sonar is 55% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.

Claude Haiku 4.5 (latest) has a 52.6% larger context than Sonar.

Field	Claude Haiku 4.5 (latest)	Sonar
Lowest input, per 1M	$0.50 +100%	$0.25
Median input, per 1M	$1.00	$1.00
Lowest output, per 1M	$2.50 +150%	$1.00
Median output, per 1M	$5.00 +400%	$1.00
Lowest unit price	$0.001 / request	—
Cost of 1M in + 200k out	$1.00 +122.2%	$0.45
Context	200K	131K +34.5%
Max output	64K +44%	114K
Providers	34	10 +70.6%
Regions	APAC, AU, EU, GLOBAL, IN, JP, US	US
Accepts	application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text	image, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	openrouter	perplexity-agent

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

aiml, edenai, fastrouter, helicone, kilo, openrouter, perplexity-agent, requesty, trustedrouter, vercel

Frequently asked questions

Which is cheaper, Claude Haiku 4.5 (latest) or Sonar?

Sonar is 50% cheaper than Claude Haiku 4.5 (latest) on input price. Sonar is 60% cheaper than Claude Haiku 4.5 (latest) on output price. Sonar is 55% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.

Which has the larger context, Claude Haiku 4.5 (latest) or Sonar?

Claude Haiku 4.5 (latest): 200K tokens; Sonar: 131K tokens.

Where can I use both Claude Haiku 4.5 (latest) and Sonar?

aiml, edenai, fastrouter, helicone, kilo, openrouter, perplexity-agent, requesty, trustedrouter, vercel