Claude Haiku 5.5 API cost
At list prices from Anthropic, Claude Haiku 5.5 costs £0.0746 per million input tokens and £0.373 per million output tokens for prompts up to 100,000 input tokens, with cached input at £0.00746. Across the standard workloads below it would cost from £18.72 a month (long-form writing) to £208.78 a month (cached-prompt assistant).
It is the 1st cheapest of 13 models at 4 workloads and 1st cheapest of 12 for the cached-prompt assistant workload. Output tokens are 91% of the bill for long-form writing but 7.7% for long-document questions. Prompt caching takes the bill for the cached-prompt assistant workload from £453.88 to £208.78 a month, 54% less. At these workloads it costs exactly the same as GPT-6 Luna (which differs in long-prompt pricing and batch pricing), because their published input, cached-input and output prices are identical. Sent through the batch API, the short chat workload would cost £28.37 a month instead of £56.73. No batch figure can be shown for the cached-prompt assistant workload: there is no verified batch cached input price for this model yet.
Prices on this page last verified on Sources
Providers publish these prices in US dollars. Pound figures are converted at £1 = US$1.3403, the Bank of England spot rate for .
Published prices
Anthropic list prices per million tokens. In our efficient tier.
| Prompt length | Input | Cached input | Output | Batch input | Batch cached input | Batch output |
|---|---|---|---|---|---|---|
| Prompts up to 100,000 input tokens | £0.0746 | £0.00746 | £0.373 | £0.0373 | n/a | £0.187 |
| Prompts over 100,000 input tokens | £0.373 | £0.0373 | £1.87 | £0.187 | n/a | £0.933 |
Cost at five standard workloads
The same traffic on every model, so the rank shows where Claude Haiku 5.5 sits. “vs cheapest” compares it with the cheapest model for that workload.
| Workload | Requests a day | Tokens in / out | Per 1,000 requests | Per month | Via batch API | Rank, all models | Rank, efficient tier | vs cheapest |
|---|---|---|---|---|---|---|---|---|
| Short chat | 10,000 | 1,000 / 300 | £0.187 | £56.73 | £28.37 | 1st of 13 | 1st of 5 | Cheapest |
| Long-document questions | 1,000 | 30,100 / 500 | £2.43 | £73.98 | £36.99 | 1st of 13 | 1st of 5 | Cheapest |
| Bulk tagging | 200,000 | 400 / 10 | £0.0336 | £204.25 | £102.12 | 1st of 13 | 1st of 5 | Cheapest |
| Long-form writing | 500 | 1,500 / 3,000 | £1.23 | £18.72 | £9.36 | 1st of 13 | 1st of 5 | Cheapest |
| Cached-prompt assistant | 20,000 | 8,000 / 400 | £0.343 | £208.78 | No verified batch cached input price for this model yet. | 1st of 12 | 1st of 4 | Cheapest |
Equal costs share a rank. “Via batch API” prices the same traffic with every request sent through the provider’s batch API, using its published batch prices.
Workload assumptions
Short chat
Short questions and answers at moderate volume.
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Instructions | 300 | No | Short instructions, treated as uncached. |
| Message and recent turns | 700 | No | Changes with every request. |
| Total | 1,000 | None cached |
- Requests a day: 10,000
- A popular in-app assistant.
- Output tokens per request: 300
- A reply of about 220 words.
- Batch API: not used
- Real-time replies.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Long-document questions
Long input with a short answer: most of the cost is input tokens.
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Document | 30,000 | No | About 22,000 words, different every time. |
| Question | 100 | No | One or two sentences. |
| Total | 30,100 | None cached |
- Requests a day: 1,000
- A research or legal team asking questions of whole documents.
- Output tokens per request: 500
- An answer of about 370 words.
- Batch API: not used
- Real-time answers.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Bulk tagging
Very high volume with a tiny output: a label per item.
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Instructions and labels | 300 | No | Short instructions, treated as uncached. |
| Item | 100 | No | A short text. |
| Total | 400 | None cached |
- Requests a day: 200,000
- Items such as tickets, reviews or records tagged as they arrive.
- Output tokens per request: 10
- One label.
- Batch API: not used
- Tagged as items arrive.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Long-form writing
A short brief and a long answer: most of the cost is output tokens.
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Brief and style notes | 1,500 | No | Different for each piece. |
| Total | 1,500 | None cached |
- Requests a day: 500
- Articles, reports or long emails drafted a day.
- Output tokens per request: 3,000
- About 2,200 words.
- Batch API: not used
- Drafts are wanted straight away.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Cached-prompt assistant
A large fixed prompt read from the prompt cache on every request.
| Part of the prompt | Tokens | Cached | Why |
|---|---|---|---|
| Instructions and tool definitions | 6,000 | Yes | The same on every request, so read from the prompt cache. |
| Conversation and request | 2,000 | No | Changes with every request. |
| Total | 8,000 | 75% cached |
- Requests a day: 20,000
- A busy assistant with long instructions and tool definitions.
- Output tokens per request: 400
- A reply of about 300 words.
- Batch API: not used
- Real-time replies.
These are stated assumptions for illustration, not measurements. Cached parts are assumed to be read from the prompt cache on every request. Token counts are the same for every model, although providers count tokens differently. Use the calculator to try your own figures.
Your traffic looks different? Enter your own figures in the calculator.
Related pages
Other models in the same tier
Sources
Sources: platform.claude.com (checked )
Providers publish these prices in US dollars. Pound figures are converted at £1 = US$1.3403, the Bank of England spot rate for .
- Tier: Provider text: "For high-volume, latency-sensitive tasks such as classification, extraction, and routing"; latency "Fastest". Fastest and high-volume: efficient. platform.claude.com (checked )
Prices are list prices as each provider publishes them, used unchanged. How the figures are calculated: methodology.