TokenSave
All comparisons · Prices checked 2026-10-01
Claude Haiku 4.5 vs Claude Sonnet 5.5: API cost comparison
For a typical chatbot reply, Claude Haiku 4.5 costs $0.0037 and Claude Sonnet 5.5 costs $0.0091 per request: Claude Haiku 4.5 is 2.5× cheaper. Claude Haiku 4.5 is cheaper in every workload below.
API prices
| Claude Haiku 4.5 | Claude Sonnet 5.5 | |
|---|---|---|
| Maker | Anthropic | Anthropic |
| Input / 1M tokens | $1 | $2 |
| Output / 1M tokens | $5 | $10 |
| Output vs input price | 5.0× | 5.0× |
| Context window | 200K tokens | 1M tokens |
| Tokens for the same English text | ~105% of GPT's count (estimate) | ~130% of GPT's count (estimate) |
Cost by workload
| Workload (per 1,000 requests) | Claude Haiku 4.5 | Claude Sonnet 5.5 | Cheaper |
|---|---|---|---|
| Chatbot reply short question plus some chat history · 1,500 in / 400 out | $3.67 | $9.10 | Claude Haiku 4.5 2.5× cheaper |
| Document Q&A (RAG) retrieved passages plus a question · 8,000 in / 500 out | $11.03 | $27.30 | Claude Haiku 4.5 2.5× cheaper |
| Coding agent step large working context, short edit · 25,000 in / 800 out | $30.45 | $75.40 | Claude Haiku 4.5 2.5× cheaper |
| Summarize a long report long input, short summary · 20,000 in / 300 out | $22.58 | $55.90 | Claude Haiku 4.5 2.5× cheaper |
| Write an article short brief, long draft · 800 in / 2,000 out | $11.34 | $28.08 | Claude Haiku 4.5 2.5× cheaper |
Claude Haiku 4.5 is cheaper on both input and output, so it costs less for every kind of request. The gap is 2.5× on input and 2.5× on output once the tokenizer difference is included.
Same text, different token counts. Each company uses its own tokenizer. By our estimate Claude Sonnet 5.5 counts about 24% more tokens than Claude Haiku 4.5 for the same English text, and the costs above already include that. Paste your own prompt into the token counter to see both counts.
Monthly cost
| Monthly volume | Claude Haiku 4.5 | Claude Sonnet 5.5 |
|---|---|---|
| 10,000 chatbot replies / month | $36.75 | $91.00 |
| 100,000 chatbot replies / month | $368 | $910 |
| 1,000,000 chatbot replies / month | $3,675 | $9,100 |
Calculate your own
Enter your typical request size and volume.
Token counts are for English text measured with GPT's tokenizer; each model's own tokenizer difference is applied automatically.
Questions
Which is cheaper, Claude Haiku 4.5 or Claude Sonnet 5.5?
For a typical chatbot reply (1,500 input and 400 output tokens), Claude Haiku 4.5 costs $0.0037 and Claude Sonnet 5.5 costs $0.0091 per request, so Claude Haiku 4.5 is 2.5× cheaper. Claude Haiku 4.5 is cheaper in every workload below.
How much do Claude Haiku 4.5 and Claude Sonnet 5.5 cost per million tokens?
Claude Haiku 4.5 costs $1 per 1M input tokens and $5 per 1M output tokens. Claude Sonnet 5.5 costs $2 input and $10 output. Prices checked 2026-10-01.
Do both models count the same text as the same number of tokens?
No. Each model family has its own tokenizer, so the same text can be a different number of tokens. The costs on this page already include that difference (estimated from GPT's tokenizer).
Related comparisons
- GPT-6 Sol vs Claude Sonnet 5.5
- Gemini 3.1 Pro vs Claude Sonnet 5.5
- GPT-6 Luna vs Claude Haiku 4.5
- Gemini 3.8 Flash vs Claude Haiku 4.5
- Claude Sonnet 5.5 vs Claude Opus 5.5
- DeepSeek V4 Pro vs Claude Sonnet 5.5
Paste a real prompt to see its exact tokens and cost on Claude Haiku 4.5, Claude Sonnet 5.5 and 30+ other models.
Open the token counter →Standard API list prices, short-context tier, no caching or batch discounts. Prices change; check each provider's pricing page before large jobs.