AI Rate Card

Claude Haiku 4.5 (latest) vs Gemini 2.5 Pro: API price and specs

Claude Haiku 4.5 (latest) is 20% cheaper than Gemini 2.5 Pro on input price.

Claude Haiku 4.5 (latest) is 50% cheaper than Gemini 2.5 Pro on output price.

Claude Haiku 4.5 (latest) is 38% cheaper than Gemini 2.5 Pro on a 1M-in / 200k-out workload.

Gemini 2.5 Pro has a 432.8% larger context than Claude Haiku 4.5 (latest).

FieldClaude Haiku 4.5 (latest)Gemini 2.5 Pro
Lowest input, per 1M$0.50$0.62 +25%
Median input, per 1M$1.00$1.25 +25%
Lowest output, per 1M$2.50$5.00 +100%
Median output, per 1M$5.00$10.00 +100%
Lowest unit price$0.001 / request—
Cost of 1M in + 200k out$1.00$1.62 +62.5%
Context200K +81.2%1.1M
Max output64K +2.3%66K
Providers3424 +29.4%
RegionsAPAC, AU, EU, GLOBAL, IN, JP, USEU, GLOBAL, US
Acceptsapplication/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, textapplication/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
Returnstexttext
TypeText modelsText models
Free optionnono
Cheapest provideropenrouterkilo

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, cortecs, deepinfra, edenai, fastrouter, google-vertex, helicone, impossibl, jiekou, kilo, meganova, nearai, ofox, openrouter, orcarouter, perplexity-agent, poe, requesty, trustedrouter, vercel, zenmux

Frequently asked questions

Which is cheaper, Claude Haiku 4.5 (latest) or Gemini 2.5 Pro?

Claude Haiku 4.5 (latest) is 20% cheaper than Gemini 2.5 Pro on input price. Claude Haiku 4.5 (latest) is 50% cheaper than Gemini 2.5 Pro on output price. Claude Haiku 4.5 (latest) is 38% cheaper than Gemini 2.5 Pro on a 1M-in / 200k-out workload.

Which has the larger context, Claude Haiku 4.5 (latest) or Gemini 2.5 Pro?

Claude Haiku 4.5 (latest): 200K tokens; Gemini 2.5 Pro: 1.1M tokens.

Where can I use both Claude Haiku 4.5 (latest) and Gemini 2.5 Pro?

abacus, aihubmix, cortecs, deepinfra, edenai, fastrouter, google-vertex, helicone, impossibl, jiekou, kilo, meganova, nearai, ofox, openrouter, orcarouter, perplexity-agent, poe, requesty, trustedrouter, vercel, zenmux