Pricing comparison
Claude Haiku 4.5 vs GPT-5
Per-token pricing, full-workload cost ladders, and monthly volume projections. Numbers sourced directly from each provider's rate card.
Anthropic
Claude Haiku 4.5
- Input
- $1.00 / 1M
- Output
- $5.00 / 1M
- Cached input
- -
- Context
- 200K
- Max output
- 64K
OpenAI
GPT-5
- Input
- $1.25 / 1M
- Output
- $10.00 / 1M
- Cached input
- $0.125 / 1M
- Context
- 400K
- Max output
- 128K
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) | Claude Haiku 4.5 | GPT-5 | Winner |
|---|---|---|---|---|
| Short prompt | 100 / 200 | $0.0011 | $0.0021 | Claude Haiku 4.5 |
| Typical request | 1,000 / 2,000 | $0.0110 | $0.0213 | Claude Haiku 4.5 |
| Long document | 10,000 / 5,000 | $0.0350 | $0.0625 | Claude Haiku 4.5 |
| Large prompt | 100,000 / 10,000 | $0.1500 | $0.2250 | Claude Haiku 4.5 |
Monthly bill at scale
Projected monthly cost at typical request volume, assuming the "typical request" shape above (1k in, 2k out).
| Traffic | Req / month | Claude Haiku 4.5 | GPT-5 | Delta |
|---|---|---|---|---|
| Small SaaS | 1,000 | $11.00 | $21.25 | Claude Haiku 4.5 -$10.25 |
| Growing product | 10,000 | $110.00 | $212.50 | Claude Haiku 4.5 -$102.50 |
| Heavy usage | 100,000 | $1,100 | $2,125 | Claude Haiku 4.5 -$1,025 |
Which should you use?
For the typical chat-shape request (~1k input, 2k output), Claude Haiku 4.5 comes out 93% cheaper. If you're picking one as the default, that's usually the right choice on cost alone.
Claude Haiku 4.5 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: GPT-5 holds 400K of input vs 200K 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).
Claude Haiku 4.5
$0.0035
per request
GPT-5
$0.0063
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, Claude Haiku 4.5 or GPT-5?
- On a typical 1,000-input / 2,000-output request, Claude Haiku 4.5 costs ~$0.0110 vs ~$0.0213 on GPT-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?
- Claude Haiku 4.5 charges $1.00 per 1M input tokens and $5.00 per 1M output tokens. GPT-5 charges $1.25 / $10.00 per 1M.
- Which has the bigger context window?
- GPT-5 is larger (400K) vs 200K on the other.
- Is there a cached-input discount on either?
- Claude Haiku 4.5 does not publish a cached-input rate. GPT-5 caches at $0.125 per 1M (90% off). Workloads with repeated static prefixes see the biggest savings.
- How fresh is this comparison?
- Claude Haiku 4.5 was re-verified on 2026-04-06 and GPT-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.
Claude Haiku 4.5 verified 2026-04-06 · GPT-5 verified 2026-04-06. Rate cards at Anthropic and OpenAI.