Model comparison - Same provider, successor
Claude Haiku 4.5 vs Claude Haiku 5.5
Claude Haiku 4.5 and Claude Haiku 5.5 are both Anthropic models. On list price, Claude Haiku 4.5 charges 10x Claude Haiku 5.5's input price ($1 vs $0.10 per 1M tokens), and Claude Haiku 4.5 charges 10x Claude Haiku 5.5's output price ($5 vs $0.50 per 1M tokens). Claude Haiku 4.5 has a 200,000-token context window and Claude Haiku 5.5 1,000,000 tokens; max output is 64,000 and 128,000 tokens per response. Claude Haiku 4.5 was released on October 15, 2025 and Claude Haiku 5.5 on October 7, 2026. Both are closed-weights models, available only through an API.
Last verified from each provider's pricing page. All sources
Side-by-side specs
| Spec | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Input / 1M tokens | $1 | $0.10 |
| Output / 1M tokens | $5 | $0.50 |
| Cache read / 1M | $0.10 | $0.01 |
| Cache write / 1M | $1.25 | $0.125 |
| Batch input / 1M | $0.50 | $0.05 |
| Batch output / 1M | $2.50 | $0.25 |
| Long-context rates above | - | 100,000 tokens |
| Context window | 200,000 | 1,000,000 |
| Max output | 64,000 | 128,000 |
| Release date | ||
| Weights | Closed | Closed |
| API model id | claude-haiku-4-5-20251001 | claude-haiku-5-5 |
| AI Gateway id | anthropic/claude-haiku-4.5 | anthropic/claude-haiku-5.5 |
| Last verified |
Prices in USD per 1M tokens at each provider's standard first-party rate. A dash means the provider does not bill that item separately or no primary page states it.
What each costs in practice
The same three workloads every model page uses, worked from each model's standard list rates. Swap in your own token counts with the math on each model's page.
| Workload | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| One agent session1M input tokens and 100K output tokens, no caching. | $1.50 | $0.15 |
| A chat app10,000 requests a day at 2K input and 500 output tokens each. | $45.00$1,350.00 per 30-day month | $4.50$135.00 per 30-day month |
| The same session at a 90% cache hit90% of the input is read from the prompt cache. The one-time cache write premium is not included. | $0.69 | $0.069 |
Show the math
Claude Haiku 4.5
- One agent sessionInput: 1M x $1 = $1.00Output: 0.1M x $5 = $0.50
- A chat appInput: 20M x $1 = $20.00Output: 5M x $5 = $25.00
- The same session at a 90% cache hitCached input: 0.9M x $0.10 = $0.09Uncached input: 0.1M x $1 = $0.10Output: 0.1M x $5 = $0.50
Claude Haiku 5.5
- One agent sessionInput: 1M x $0.10 = $0.10Output: 0.1M x $0.50 = $0.05
- A chat appInput: 20M x $0.10 = $2.00Output: 5M x $0.50 = $2.50
- The same session at a 90% cache hitCached input: 0.9M x $0.01 = $0.009Uncached input: 0.1M x $0.10 = $0.01Output: 0.1M x $0.50 = $0.05
Benchmarks under the same setting
No board in the benchmark directory lists both Claude Haiku 4.5 and Claude Haiku 5.5 under the same setting, so there is no like-for-like score to show here.
Model pages
FAQ
How do Claude Haiku 4.5 and Claude Haiku 5.5 compare on price?
On list price, Claude Haiku 4.5 charges 10x Claude Haiku 5.5's input price ($1 vs $0.10 per 1M tokens), and Claude Haiku 4.5 charges 10x Claude Haiku 5.5's output price ($5 vs $0.50 per 1M tokens). For one agent session of 1M input and 100K output tokens with no caching, that is $1.50 on Claude Haiku 4.5 and $0.15 on Claude Haiku 5.5. Prices are each provider's first-party list rates, verified October 17, 2026 and October 17, 2026.
What are the context windows of Claude Haiku 4.5 and Claude Haiku 5.5?
Claude Haiku 4.5 has a 200,000-token context window and Claude Haiku 5.5 1,000,000 tokens; max output is 64,000 and 128,000 tokens per response.
Are Claude Haiku 4.5 and Claude Haiku 5.5 open weights?
Claude Haiku 4.5 is closed-weights and is called through Anthropic's API as claude-haiku-4-5-20251001. Claude Haiku 5.5 is closed-weights and is called through Anthropic's API as claude-haiku-5-5.
More comparisons
- Claude Haiku 5.5 vs GPT-6 LunaSimilar price, same tier
- Claude Haiku 5.5 vs DeepSeek V4.1 FlashOpen weights vs closed
- Claude Haiku 5.5 vs GLM-5.3-FlashSimilar price, same tier
- Claude Haiku 5.5 vs Qwen3.8-FlashSimilar price, same tier
- Claude Haiku 5.5 vs MiniMax-M3Open weights vs closed
- Claude Haiku 5.5 vs Mistral Small 4Similar price, same tier
Sources
Claude Haiku 4.5 verified from platform.claude.com; Claude Haiku 5.5 verified from platform.claude.com. This page is as current as the older of the two: .
- https://platform.claude.com/docs/en/about-claude/pricing
- https://platform.claude.com/docs/en/models/haiku-4-5/overview
- https://platform.claude.com/docs/en/about-claude/models/overview
- https://platform.claude.com/docs/en/release-notes/overview
- https://platform.claude.com/docs/en/about-claude/model-deprecations
- https://platform.claude.com/docs/en/models/haiku-5-5/overview
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.