Anthropic
Claude Haiku 4.5 token cost
Fast, low-cost Claude tier for classification, extraction, and high-volume chat.
Published list rates
Input
$1.00
per 1M tokens
Output
$5.00
per 1M tokens
Cached input
$0.1
per 1M tokens
Context window
200,000
tokens
Pricing source: Anthropic Claude pricing
Estimate cost
Estimate from text
Calculate from a token total
Project monthly volume
Daily requests × tokens per request × 30 days.
Estimated cost
- Estimated tokens
- —
- Characters
- —
- Words
- —
- Input tokens
- —
- Output tokens
- —
- Input cost
- —
- Output cost
- —
- Total cost
- —
- Combined price per 1M tokens
- —
- Estimated monthly cost
- —
- Estimated daily cost
- —
Cost as volume grows
Read down to see Claude Haiku 4.5 get more expensive as tokens grow. The last column is a typical mix: 70% input, 30% output.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.000001 | $0.000005 | $0.000002 |
| 10 | $0.00001 | $0.00005 | $0.000022 |
| 100 | $0.0001 | $0.0005 | $0.00022 |
| 200 | $0.0002 | $0.001 | $0.00044 |
| 300 | $0.0003 | $0.0015 | $0.00066 |
| 400 | $0.0004 | $0.002 | $0.00088 |
| 500 | $0.0005 | $0.0025 | $0.0011 |
| 1,000 | $0.001 | $0.005 | $0.0022 |
| 2,000 | $0.002 | $0.01 | $0.0044 |
| 5,000 | $0.005 | $0.025 | $0.011 |
| 10,000 | $0.01 | $0.05 | $0.022 |
| 25,000 | $0.025 | $0.125 | $0.055 |
| 50,000 | $0.05 | $0.25 | $0.11 |
| 100,000 | $0.1 | $0.5 | $0.22 |
| 250,000 | $0.25 | $1.25 | $0.55 |
| 500,000 | $0.5 | $2.50 | $1.10 |
| 1,000,000 | $1.00 | $5.00 | $2.20 |
| 5,000,000 | $5.00 | $25.00 | $11.00 |
| 10,000,000 | $10.00 | $50.00 | $22.00 |
| 50,000,000 | $50.00 | $250.00 | $110.00 |
| 100,000,000 | $100.00 | $500.00 | $220.00 |
| 500,000,000 | $500.00 | $2,500.00 | $1,100.00 |
| 1,000,000,000 | $1,000.00 | $5,000.00 | $2,200.00 |
| 10,000,000,000 | $10,000.00 | $50,000.00 | $22,000.00 |
| 100,000,000,000 | $100,000.00 | $500,000.00 | $220,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many Claude Haiku 4.5 tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 10,000 | 2,000 | 4,545 |
| $0.1 | 100,000 | 20,000 | 45,455 |
| $0.5 | 500,000 | 100,000 | 227,273 |
| $1.00 | 1M | 200,000 | 454,545 |
| $5.00 | 5M | 1M | 2.27M |
| $10.00 | 10M | 2M | 4.55M |
| $20.00 | 20M | 4M | 9.09M |
| $25.00 | 25M | 5M | 11.4M |
| $30.00 | 30M | 6M | 13.6M |
| $50.00 | 50M | 10M | 22.7M |
| $100.00 | 100M | 20M | 45.5M |
| $250.00 | 250M | 50M | 113.6M |
| $500.00 | 500M | 100M | 227.3M |
| $1,000.00 | 1B | 200M | 454.5M |
| $5,000.00 | 5B | 1B | 2.27B |
| $10,000.00 | 10B | 2B | 4.55B |
At these rates
- A workload with 70% input and 30% output costs $2.20 per 1 million total tokens and $220.00 per 100 million.
- At the same token count, output costs 5 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 200,000-token context window with input alone would cost about $0.2, before any output.
- Cached input is $0.1 per million, 90% below standard input when the workload meets the provider’s cache rules.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.