AI Rate CardClaude Haiku 4.5 (latest) vs GPT-5.1 Codex mini: API price and specs
GPT-5.1 Codex mini is 56% cheaper than Claude Haiku 4.5 (latest) on input price.
GPT-5.1 Codex mini is 28% cheaper than Claude Haiku 4.5 (latest) on output price.
GPT-5.1 Codex mini is 42% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.
GPT-5.1 Codex mini has a 100% larger context than Claude Haiku 4.5 (latest).
| Field | Claude Haiku 4.5 (latest) | GPT-5.1 Codex mini |
|---|---|---|
| Lowest input, per 1M | $0.50 +127.3% | $0.22 |
| Median input, per 1M | $1.00 +300% | $0.25 |
| Lowest output, per 1M | $2.50 +38.9% | $1.80 |
| Median output, per 1M | $5.00 +150% | $2.00 |
| Lowest unit price | $0.001 / request | — |
| Cost of 1M in + 200k out | $1.00 +72.4% | $0.58 |
| Context | 200K +50% | 400K |
| Max output | 64K +50% | 128K |
| Providers | 34 | 15 +55.9% |
| Regions | APAC, AU, EU, GLOBAL, IN, JP, US | GLOBAL |
| 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 | image, text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | openrouter | poe |
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
aihubmix, aiml, azure, edenai, helicone, impossibl, jiekou, kilo, ofox, opencode, openrouter, orcarouter, poe, vercel, zenmux
Frequently asked questions
Which is cheaper, Claude Haiku 4.5 (latest) or GPT-5.1 Codex mini?
GPT-5.1 Codex mini is 56% cheaper than Claude Haiku 4.5 (latest) on input price. GPT-5.1 Codex mini is 28% cheaper than Claude Haiku 4.5 (latest) on output price. GPT-5.1 Codex mini is 42% 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-5.1 Codex mini?
Claude Haiku 4.5 (latest): 200K tokens; GPT-5.1 Codex mini: 400K tokens.
Where can I use both Claude Haiku 4.5 (latest) and GPT-5.1 Codex mini?
aihubmix, aiml, azure, edenai, helicone, impossibl, jiekou, kilo, ofox, opencode, openrouter, orcarouter, poe, vercel, zenmux