Claude Haiku 4.5 vs Claude Sonnet 4.6 — Side-by-side pricing
Side-by-side API pricing and tokenizer details for Claude Haiku 4.5 (Anthropic) and Claude Sonnet 4.6 (Anthropic).
Side-by-side pricing
| Feature | Claude Haiku 4.5 | Claude Sonnet 4.6 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Input (per 1M tokens) | $1.00 | $3.00 |
| Output (per 1M tokens) | $5.00 | $15.00 |
| Context caching | Yes — 90% off cached tokens | Yes — 90% off cached tokens |
| Batch API discount | 50% off | 50% off |
| Context window | 200K tokens | 1M tokens |
| Tokenizer | Anthropic tokenizer | Anthropic tokenizer |
Real-world cost example
1,000 API requests per month, each with 500 input tokens and 200 output tokens (500K input + 200K output total).
Claude Haiku 4.5
$1.5000
Input: $0.5000 +Output: $1.0000
Claude Sonnet 4.6
$4.5000
Input: $1.5000 +Output: $3.0000
Claude Haiku 4.5 is 67% cheaper for this workload — saving $3.0000 per month at this volume.
Frequently asked questions
Yes, Claude Haiku 4.5 is cheaper for the typical workload above. At $1.00/1M input and $5.00/1M output tokens, it costs $1.5000 versus $4.5000 for Claude Sonnet 4.6 — a 67% difference. Costs scale linearly with request volume, so larger workloads amplify this gap.
Claude Haiku 4.5 supports a 200K token context window. Claude Sonnet 4.6 supports a 1M token context window. A larger context window lets you include more text — documents, conversation history, or code — in a single API call.
Claude Haiku 4.5 supports context caching (90% off repeated tokens). It offers a 50% Batch API discount. Claude Sonnet 4.6 supports context caching (90% off repeated tokens). It offers a 50% Batch API discount.
Yes, both Claude Haiku 4.5 and Claude Sonnet 4.6 use the Anthropic tokenizer. The same text produces identical token counts on both models, so any cost difference is purely due to the rate each provider charges per token.
Claude Haiku 4.5 (Anthropic): $1 input / $5 output per 1M tokens. Claude Sonnet 4.6 (Anthropic): $3 input / $15 output per 1M tokens. Rates shown before caching or batch discounts.
For an 80% output / 20% input workload — typical for code generation or long-form writing — Claude Haiku 4.5 costs $4.2000 per 1M total tokens and Claude Sonnet 4.6 costs $12.6000. Claude Haiku 4.5 is 67% cheaper for this pattern. For your exact ratio, paste a real prompt into the calculator above.
Claude Haiku 4.5 has a 200K-token context window — approximately 150K words or ~600 pages of standard text. Claude Sonnet 4.6 has a 1M-token context window — approximately 750K words or ~3K pages. (Estimates assume ~0.75 words per token.)
Calculate costs for your actual prompt
Paste your prompt into the calculator and get exact token counts using each model's real tokenizer — all in your browser.
Open calculator