Claude Haiku 4.5 (latest) vs Gemini 3.5 Flash: API price and specs

Claude Haiku 4.5 (latest) is 33% cheaper than Gemini 3.5 Flash on input price.

Claude Haiku 4.5 (latest) is 33% cheaper than Gemini 3.5 Flash on output price.

Claude Haiku 4.5 (latest) is 33% cheaper than Gemini 3.5 Flash on a 1M-in / 200k-out workload.

Gemini 3.5 Flash has a 424.3% larger context than Claude Haiku 4.5 (latest).

Field	Claude Haiku 4.5 (latest)	Gemini 3.5 Flash
Lowest input, per 1M	$0.50	$0.75 +50%
Median input, per 1M	$1.00	$1.50 +50%
Lowest output, per 1M	$2.50	$3.75 +50%
Median output, per 1M	$5.00	$9.00 +80%
Lowest unit price	$0.001 / request	$0.001 / request
Cost of 1M in + 200k out	$1.00	$1.50 +50%
Context	200K +80.9%	1M
Max output	64K +2.3%	66K
Providers	34	25 +26.5%
Regions	APAC, AU, EU, GLOBAL, IN, JP, US	APAC, EU, GLOBAL, US
Accepts	application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text	application/pdf, audio, audio/aac, audio/aiff, audio/alaw, audio/flac, audio/l16, audio/m4a, audio/mp3, audio/mpeg, audio/mulaw, audio/ogg, audio/opus, audio/wav, audio/webm, file, image, image/heic, image/heif, image/jpeg, image/png, image/webp, pdf, text, video, video/3gpp, video/avi, video/mov, video/mp4, video/mpeg, video/mpg, video/webm, video/wmv, video/x-flv
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	openrouter	aihubmix

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

abacus, aihubmix, aiml, cometapi, cortecs, deepinfra, edenai, fastrouter, github-copilot, google-vertex, impossibl, jiekou, kilo, meganova, nearai, ofox, opencode, openrouter, orcarouter, poe, requesty, trustedrouter, vercel, xpersona, zenmux

Frequently asked questions

Which is cheaper, Claude Haiku 4.5 (latest) or Gemini 3.5 Flash?

Claude Haiku 4.5 (latest) is 33% cheaper than Gemini 3.5 Flash on input price. Claude Haiku 4.5 (latest) is 33% cheaper than Gemini 3.5 Flash on output price. Claude Haiku 4.5 (latest) is 33% cheaper than Gemini 3.5 Flash on a 1M-in / 200k-out workload.

Which has the larger context, Claude Haiku 4.5 (latest) or Gemini 3.5 Flash?

Claude Haiku 4.5 (latest): 200K tokens; Gemini 3.5 Flash: 1M tokens.

Where can I use both Claude Haiku 4.5 (latest) and Gemini 3.5 Flash?