Claude Haiku 5.5 vs GPT-6 Luna: API price and specs

GPT-6 Luna has a 5% larger context than Claude Haiku 5.5.

Field	Claude Haiku 5.5	GPT-6 Luna
Lowest input, per 1M	$0.05	$0.05
Median input, per 1M	$0.10	$0.10
Lowest output, per 1M	$0.25	$0.25
Median output, per 1M	$0.50	$0.50
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.10	$0.10
Context	1M +4.8%	1.1M
Max output	128K	128K
Providers	33	29 +12.1%
Regions	AU, EU, GLOBAL, JP, US	EU, GLOBAL, US
Accepts	application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text	application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	iteracompute	openrouter

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

302ai, abacus, aihubmix, aiml, amazon-bedrock, azure, cometapi, cortecs, digitalocean, edenai, fastrouter, github-copilot, impossibl, iteracompute, jiekou, kenari, kilo, meganova, nearai, ofox, opencode, opencode-go, openrouter, perplexity-agent, requesty, trustedrouter, vercel, zenmux

Frequently asked questions

Which has the larger context, Claude Haiku 5.5 or GPT-6 Luna?

Claude Haiku 5.5: 1M tokens; GPT-6 Luna: 1.1M tokens.

Where can I use both Claude Haiku 5.5 and GPT-6 Luna?