Claude Haiku 4.5
AnthropicUpdated July 2026. Claude Haiku 4.5 by Anthropic: $1.00/M cache-miss input, $5.00/M output tokens. Cached input: $0.1/M. 200K context, 64K max output. Vision & Function Calling. Free calculator + compare 40+ models.
Input Price
$1.00
cache miss / 1M tokens
Cached Input
$0.1
per 1M tokens
Output Price
$5.00
per 1M tokens
Context Window
200K
tokens
Specifications
| Provider | Anthropic |
| Model ID | claude-haiku-4-5 |
| Input Price | $1 / 1M cache-miss tokens |
| Cached Input Price | $0.1 / 1M tokens |
| Output Price | $5 / 1M tokens |
| Context Window | 200K tokens |
| Max Output | 64K tokens |
| Capabilities | textvisionfunction_calling |
| Release Date | 2025-10 |
| Pricing Source | Official Anthropic pricing |
| Price Verified | 2026-06-14 · Claude Fable 5 and Mythos 5 were released on 2026-06-09 but customer access was suspended on 2026-06-12, so they are not listed as usable calculator models. |
| Notes | Fastest Claude model. 200K context, 64K max output. |
Monthly Cost Estimates
Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.
| Daily Tokens | Monthly Cost | Annual Cost |
|---|---|---|
| 10K | $0.90 | $10.80 |
| 50K | $4.50 | $54.00 |
| 100K | $9.00 | $108.00 |
| 500K | $45.00 | $540.00 |
| 1.0M | $90.00 | $1080.00 |
About Claude Haiku 4.5
Claude Haiku 4.5 is a large language model by Anthropic. It features a 200K token context window with up to 64K tokens of output per request. The model supports 3 capabilities: text, vision, function_calling.
At $1 per million cache-miss input tokens and $5 per million output tokens, Claude Haiku 4.5 is positioned as a mid-range option in the Anthropic lineup. Repeated prefix input can be charged at $0.1 per million cached tokens. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.
Claude Haiku 4.5 Key Details
- Pricing: $1/M cache-miss input tokens, $0.1/M cached input tokens, $5/M output tokens
- Context window: 200K tokens — suitable for large documents and codebases
- Max output: 64K tokens per response
- Capabilities: text, vision, function_calling
- Highlights: Fastest Claude model. 200K context, 64K max output.
- Released: 2025-10
Other Anthropic Models
Similar Price Range
Related Tools
FAQ
How much does Claude Haiku 4.5 cost?
Claude Haiku 4.5 costs $1 per million cache-miss input tokens and $5 per million output tokens. Cached input costs $0.1 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $10.50/month before cache-hit savings.
What is Claude Haiku 4.5's context window?
Claude Haiku 4.5 supports a context window of 200K tokens. This means your combined input prompt and output response can be up to 200K tokens. The maximum output per response is 64K tokens.
Is Claude Haiku 4.5 good for my use case?
Claude Haiku 4.5 supports text, vision, function_calling. As a mid-range model, it balances capability and cost for most production use cases. Use our Pricing Calculator to compare with alternatives.