AI Rate CardClaude Haiku 4.5 (latest) vs GPT-5 Mini: API price and specs
GPT-5 Mini is 75% cheaper than Claude Haiku 4.5 (latest) on input price.
GPT-5 Mini is 60% cheaper than Claude Haiku 4.5 (latest) on output price.
GPT-5 Mini is 68% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.
GPT-5 Mini has a 100% larger context than Claude Haiku 4.5 (latest).
| Field | Claude Haiku 4.5 (latest) | GPT-5 Mini |
|---|---|---|
| Lowest input, per 1M | $0.50 +300% | $0.12 |
| Median input, per 1M | $1.00 +300% | $0.25 |
| Lowest output, per 1M | $2.50 +150% | $1.00 |
| Median output, per 1M | $5.00 +150% | $2.00 |
| Lowest unit price | $0.001 / request | — |
| Cost of 1M in + 200k out | $1.00 +207.7% | $0.33 |
| Context | 200K +50% | 400K |
| Max output | 64K +50% | 128K |
| Providers | 34 | 27 +20.6% |
| Regions | APAC, AU, EU, GLOBAL, IN, JP, US | EU, GLOBAL, US |
| Accepts | application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text | 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 | openrouter | 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
abacus, aihubmix, aiml, azure, cometapi, cortecs, digitalocean, edenai, fastrouter, github-copilot, 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 GPT-5 Mini?
GPT-5 Mini is 75% cheaper than Claude Haiku 4.5 (latest) on input price. GPT-5 Mini is 60% cheaper than Claude Haiku 4.5 (latest) on output price. GPT-5 Mini is 68% 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 GPT-5 Mini?
Claude Haiku 4.5 (latest): 200K tokens; GPT-5 Mini: 400K tokens.
Where can I use both Claude Haiku 4.5 (latest) and GPT-5 Mini?
abacus, aihubmix, aiml, azure, cometapi, cortecs, digitalocean, edenai, fastrouter, github-copilot, helicone, impossibl, jiekou, kilo, meganova, nearai, ofox, openrouter, orcarouter, perplexity-agent, poe, requesty, trustedrouter, vercel, zenmux