Claude Haiku 4.5 (latest) pricing, context window and limits
Claude Haiku 4.5 (latest) costs $1 per million input tokens and $5 per million output tokens at Anthropic list price. It accepts up to 200,000 tokens of context and returns up to 64,000 tokens.
- Model id
claude-haiku-4-5 - Snapshot
What does Claude Haiku 4.5 (latest) cost?
| Input | $1 |
|---|---|
| Output | $5 |
| Cached input (read) | $0.1 |
| Cache write | $1.25 |
US dollars per million tokens. A dash means no price is published.
How much can Claude Haiku 4.5 (latest) read and write?
| Context window | 200,000 |
|---|---|
| Max output | 64,000 |
What can Claude Haiku 4.5 (latest) do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text, image, pdf |
| Output | text |
What does a request to Claude Haiku 4.5 (latest) cost?
| A typical request: 1,000 tokens in, 500 out | $0.0035 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.015 |
| 1,000 typical requests | $3.5 |
| 1 million tokens in and 1 million out | $6 |
Input read from the provider's prompt cache costs $0.1 per million tokens instead of $1, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.0026 instead of $0.0035.
Among 16 Anthropic models with a published price, Claude Haiku 4.5 (latest) is the cheapest by input price. Its context window is the 13th largest of 16. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Claude Haiku 4.5 (latest) through DVARA?
Configure the anthropic provider in the DVARA LLM Gateway and send the model id claude-haiku-4-5. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.
Which other Anthropic models are there?
- Claude Fable 5.1$10 in · $50 out · 1M context
- Claude Haiku 4.5$1 in · $5 out · 200K context
- Claude Fable 5$10 in · $50 out · 1M context
- Claude Opus 4.5 (latest)$5 in · $25 out · 200K context
- Claude Opus 4.5$5 in · $25 out · 200K context
- Claude Opus 4.6$5 in · $25 out · 1M context
- Claude Opus 4.7$5 in · $25 out · 1M context
- Claude Opus 4.8$5 in · $25 out · 1M context
- Claude Opus 5$5 in · $25 out · 1M context
- Claude Opus 5.5$4 in · $20 out · 1M context
- Claude Sonnet 4.5 (latest)$3 in · $15 out · 1M context
- Claude Sonnet 4.5$3 in · $15 out · 1M context
Which models from other providers are similar to Claude Haiku 4.5 (latest)?
These are the closest in context window and input price, one per provider.
- Claude Haiku 4.5Amazon Bedrock · $1 in · $5 out · 200K context
- GLM-5Zhipu GLM · $1 in · $3.2 out · 205K context
- o3-miniOpenAI · $1.1 in · $4.4 out · 200K context
- Grok Build 0.1xAI Grok · $1 in · $2 out · 256K context
- Kimi K2.6Moonshot AI · $0.95 in · $4 out · 262K context