High-volume, cost-sensitive work
Choose Claude Haiku 5.5
Claude Haiku 5.5 costs 90% less on a typical mix of three input tokens for every output token ($0.20 against $2.00 per million tokens).
Choose Claude Haiku 5.5 for high-volume, cost-sensitive work, writing and code generation, reused prompts and documents (RAG, agents), very long inputs and the latest release; on the other points the two are level or the data is missing.
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Choose Claude Haiku 5.5
Claude Haiku 5.5 costs 90% less on a typical mix of three input tokens for every output token ($0.20 against $2.00 per million tokens).
Choose Claude Haiku 5.5
Claude Haiku 5.5 charges $0.50 per million output tokens, against $5.00 for Claude Haiku 4.5. Output dominates the bill when answers are long.
Choose Claude Haiku 5.5
Claude Haiku 5.5 charges $0.01 per million cached input tokens, against $0.10 for Claude Haiku 4.5.
Choose Claude Haiku 5.5
Claude Haiku 5.5 reads up to 1M tokens per request, against 200k for Claude Haiku 4.5.
Choose Claude Haiku 5.5
Claude Haiku 5.5 is the newer release (October 2026, against October 2025 for Claude Haiku 4.5).
| Volume | Claude Haiku 4.5 | Claude Haiku 5.5 | Difference |
|---|---|---|---|
| Prototype: 1M input, 250K output tokens | $2.25 | $0.23 | Claude Haiku 5.5, $2.03 less |
| Production: 20M input, 5M output tokens | $45.00 | $4.50 | Claude Haiku 5.5, $40.50 less |
| Scale: 500M input, 100M output tokens | $1,000 | $100.00 | Claude Haiku 5.5, $900.00 less |
Standard rates, without caching or batch discounts. Volumes are per month.
| Claude Haiku 4.5 | Claude Haiku 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Category | Language models | Language models |
| Status | Legacy | Generally available |
| Headline price | $2.00 / 1M tokens | $0.20 / 1M tokens |
| Input | $1.00 / 1M tokens | $0.10 / 1M tokens |
| Output | $5.00 / 1M tokens | $0.50 / 1M tokens |
| Cached input | $0.10 / 1M tokens | $0.01 / 1M tokens |
| Context window | 200k | 1M |
| Max output | 64k | 128k |
| Released | October 2025 | October 2026 |
| Knowledge cutoff | No data | June 2026 |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API |
| API model id | claude-haiku-4-5-20251001 | claude-haiku-5-5 |
Leader in bold.
| Benchmark | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| Intelligence Index | No data | 43.4 |
| SciCode | No data | 55% |
| Humanity's Last Exam | No data | 44.4% |
| Long-context reasoning (AA-LCR) | No data | 82.7% |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Choose Claude Haiku 5.5 for high-volume, cost-sensitive work, writing and code generation, reused prompts and documents (RAG, agents), very long inputs and the latest release; on the other points the two are level or the data is missing.
Claude Haiku 5.5 is 90% cheaper than Claude Haiku 4.5 at the headline price ($0.20 / 1M tokens vs $2.00 / 1M tokens).
Claude Haiku 5.5 reads more per request: 1M tokens against 200k.
Claude Haiku 4.5 is made by Anthropic and Claude Haiku 5.5 by Anthropic. Claude Haiku 5.5 is 90% cheaper than Claude Haiku 4.5 at the headline price ($0.20 / 1M tokens vs $2.00 / 1M tokens). Claude Haiku 5.5 reads more per request: 1M tokens against 200k. Claude Haiku 5.5 is the newer model (October 2026, against October 2025).
At 20 million input and 5 million output tokens a month, Claude Haiku 4.5 costs $45.00 and Claude Haiku 5.5 costs $4.50, at standard rates.
Claude Haiku 5.5 was released on October 2026 and Claude Haiku 4.5 on October 2025.