Pricing comparison
GPT-4o mini vs Claude Haiku 4.5
Per-token pricing, full-workload cost ladders, and monthly volume projections. Numbers sourced directly from each provider's rate card.
OpenAI
GPT-4o mini
- Input
- $0.15 / 1M
- Output
- $0.60 / 1M
- Cached input
- $0.075 / 1M
- Context
- 128K
- Max output
- 16K
Anthropic
Claude Haiku 4.5
- Input
- $1.00 / 1M
- Output
- $5.00 / 1M
- Cached input
- -
- Context
- 200K
- Max output
- 64K
Cost per request
Four common workload shapes, input tokens and a 1:2 output ratio (a standard chat/completion pattern). Long-context surcharges apply automatically where the provider charges them.
| Scenario | Tokens (in / out) | GPT-4o mini | Claude Haiku 4.5 | Winner |
|---|---|---|---|---|
| Short prompt | 100 / 200 | $0.0001 | $0.0011 | GPT-4o mini |
| Typical request | 1,000 / 2,000 | $0.0013 | $0.0110 | GPT-4o mini |
| Long document | 10,000 / 5,000 | $0.0045 | $0.0350 | GPT-4o mini |
| Large prompt | 100,000 / 10,000 | $0.0210 | $0.1500 | GPT-4o mini |
Monthly bill at scale
Projected monthly cost at typical request volume, assuming the "typical request" shape above (1k in, 2k out).
| Traffic | Req / month | GPT-4o mini | Claude Haiku 4.5 | Delta |
|---|---|---|---|---|
| Small SaaS | 1,000 | $1.35 | $11.00 | GPT-4o mini -$9.65 |
| Growing product | 10,000 | $13.50 | $110.00 | GPT-4o mini -$96.50 |
| Heavy usage | 100,000 | $135.00 | $1,100 | GPT-4o mini -$965.00 |
Which should you use?
For the typical chat-shape request (~1k input, 2k output), GPT-4o mini comes out 715% cheaper. If you're picking one as the default, that's usually the right choice on cost alone.
GPT-4o mini wins on both sides of the bill - cheaper input and cheaper output. If the quality gap is in your favour, there's no cost argument for the other side.
Context window differs: Claude Haiku 4.5 holds 200K of input vs 128K on the other side. If you regularly push past the smaller ceiling, the comparison ends there.
Live cost calculator
Type in any token counts - both prices update instantly. Uses base input/output rates (no cache discount, no long-context tier).
GPT-4o mini
$0.0004
per request
Claude Haiku 4.5
$0.0035
per request
Try both in the estimator →
Drop your actual prompt in, tokens are counted with the provider's own tokenizer, and the dollar number matches what lands on your invoice.
Frequently asked
- Which is cheaper, GPT-4o mini or Claude Haiku 4.5?
- On a typical 1,000-input / 2,000-output request, GPT-4o mini costs ~$0.0013 vs ~$0.0110 on Claude Haiku 4.5. Input or output rates can flip the answer for very lopsided workloads - see the cost ladder above.
- What's the difference in per-token pricing?
- GPT-4o mini charges $0.15 per 1M input tokens and $0.60 per 1M output tokens. Claude Haiku 4.5 charges $1.00 / $5.00 per 1M.
- Which has the bigger context window?
- Claude Haiku 4.5 is larger (200K) vs 128K on the other.
- Is there a cached-input discount on either?
- GPT-4o mini caches at $0.075 per 1M (50% off). Claude Haiku 4.5 does not publish a cached-input rate. Workloads with repeated static prefixes see the biggest savings.
- How fresh is this comparison?
- GPT-4o mini was re-verified on 2026-04-06 and Claude Haiku 4.5 on 2026-04-06 against each provider's published rate card. Calcis re-checks every row on a rolling schedule and re-deploys when a provider changes pricing.
GPT-4o mini verified 2026-04-06 · Claude Haiku 4.5 verified 2026-04-06. Rate cards at OpenAI and Anthropic.