Claude Haiku 4.5 pricing
The fast, cheap end of the Claude family, priced at a third of Sonnet while keeping the same context window. Suited to classification, extraction, and high-volume routing.
List prices checked
By Anthropic · Balanced tier
Token pricing
Per million tokens, from the official price list.
| Token type | Price per 1M | Notes |
|---|---|---|
| Input | $1.00 | Everything you send, including the system prompt |
| Output | $5.00 | Everything the model generates, reasoning tokens included |
| Cached input | $0.100 | Repeated prefixes served from cache |
| Blended (3:1) | $2.00 | One number for ranking, at three input tokens per output token |
Source: Anthropic pricing (August 2026). Published list prices only — committed-use discounts, regional variation, and per-request charges are not included. Last checked against the vendor’s page on 2026-08-07.
Capabilities
| Property | Value |
|---|---|
| Context window | 200K tokens |
| Max output | 64K tokens |
| Inputs accepted | text, image |
| Cost to fill the context once | $0.20 |
What it costs per month
Token prices applied to three workload shapes. Input-heavy and output-heavy workloads rank models very differently.
In-app chat assistant
A support or help assistant handling a few thousand conversations a month, with short prompts and short answers.
$45/mo
- 20M input tokens$20
- 5M output tokens$25
- If fully cached$27
RAG over documents
Retrieval-augmented answering where each request stuffs several retrieved passages into the prompt, so input dominates.
$375/mo
- 300M input tokens$300
- 15M output tokens$75
- If fully cached$105
Coding agent
An agentic loop that reads files and writes patches, generating heavy output and re-sending large context on every turn.
$900/mo
- 400M input tokens$400
- 100M output tokens$500
- If fully cached$540
Claude Haiku 4.5 vs other balanced models
Same capability tier, ranked by blended token price.
| Model | Input | Output | Context | Compare |
|---|---|---|---|---|
| OpenAI o4-mini | $1.10 | $4.40 | 200K | Head to head |
| Gemini 2.5 Flash | $0.300 | $2.50 | 1M | Head to head |
| Grok 3 mini | $0.300 | $0.500 | 131K | Head to head |
| Codestral | $0.300 | $0.900 | 262K | Head to head |
| GPT-5 mini | $0.250 | $2.00 | 400K | Head to head |
| DeepSeek-V4-Flash | $0.140 | $0.280 | 1M | Head to head |
Questions about pricing
- How much does the Claude Haiku 4.5 API cost in 2026?
- $1.00 per million input tokens and $5.00 per million output tokens, from Anthropic's published pricing. The table above converts that into a monthly figure for three common workloads.
- What is the Claude Haiku 4.5 context window?
- 200K tokens, with up to 64K tokens of output per request. Filling the window costs whatever that many input tokens cost — at $1.00 per million, a single full-context request runs about $0.20.
- Does Claude Haiku 4.5 support prompt caching?
- Yes. Cached input is billed at $0.100 per million tokens, roughly 10× cheaper than uncached input. For an agent that resends the same system prompt and file context on every turn, that discount usually matters more than the headline rate does.
- Is Claude Haiku 4.5 cheaper than the alternatives?
- On a blended 3:1 input-to-output basis it works out at $2.00 per million tokens. The comparison table below ranks it against the other balanced models in the dataset, and the head-to-head pages model both against identical workloads.