High-volume, cost-sensitive work
Choose Claude Sonnet 5.5
Claude Sonnet 5.5 costs 33% less on a typical mix of three input tokens for every output token ($4.00 against $6.00 per million tokens).
Choose Claude Sonnet 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 Sonnet 5.5
Claude Sonnet 5.5 costs 33% less on a typical mix of three input tokens for every output token ($4.00 against $6.00 per million tokens).
Choose Claude Sonnet 5.5
Claude Sonnet 5.5 charges $10.00 per million output tokens, against $15.00 for Claude Sonnet 4.5. Output dominates the bill when answers are long.
Choose Claude Sonnet 5.5
Claude Sonnet 5.5 charges $0.10 per million cached input tokens, against $0.30 for Claude Sonnet 4.5.
Choose Claude Sonnet 5.5
Claude Sonnet 5.5 reads up to 1M tokens per request, against 200k for Claude Sonnet 4.5.
Choose Claude Sonnet 5.5
Claude Sonnet 5.5 is the newer release (September 2026, against September 2025 for Claude Sonnet 4.5).
| Volume | Claude Sonnet 4.5 | Claude Sonnet 5.5 | Difference |
|---|---|---|---|
| Prototype: 1M input, 250K output tokens | $6.75 | $4.50 | Claude Sonnet 5.5, $2.25 less |
| Production: 20M input, 5M output tokens | $135.00 | $90.00 | Claude Sonnet 5.5, $45.00 less |
| Scale: 500M input, 100M output tokens | $3,000 | $2,000 | Claude Sonnet 5.5, $1,000 less |
Standard rates, without caching or batch discounts. Volumes are per month.
| Claude Sonnet 4.5 | Claude Sonnet 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Category | Language models | Language models |
| Status | Deprecated | Generally available |
| Headline price | $6.00 / 1M tokens | $4.00 / 1M tokens |
| Input | $3.00 / 1M tokens | $2.00 / 1M tokens |
| Output | $15.00 / 1M tokens | $10.00 / 1M tokens |
| Cached input | $0.30 / 1M tokens | $0.10 / 1M tokens |
| Context window | 200k | 1M |
| Max output | 64k | 128k |
| Released | September 2025 | September 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-sonnet-4-5-20250929 | claude-sonnet-5-5 |
Leader in bold.
| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 5.5 |
|---|---|---|
| Intelligence Index | No data | 56 |
| SciCode | No data | 61% |
| Humanity's Last Exam | No data | 55% |
| 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 Sonnet 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 Sonnet 5.5 is 33% cheaper than Claude Sonnet 4.5 at the headline price ($4.00 / 1M tokens vs $6.00 / 1M tokens).
Claude Sonnet 5.5 reads more per request: 1M tokens against 200k.
Claude Sonnet 4.5 is made by Anthropic and Claude Sonnet 5.5 by Anthropic. Claude Sonnet 5.5 is 33% cheaper than Claude Sonnet 4.5 at the headline price ($4.00 / 1M tokens vs $6.00 / 1M tokens). Claude Sonnet 5.5 reads more per request: 1M tokens against 200k. Claude Sonnet 5.5 is the newer model (September 2026, against September 2025).
At 20 million input and 5 million output tokens a month, Claude Sonnet 4.5 costs $135.00 and Claude Sonnet 5.5 costs $90.00, at standard rates.
Claude Sonnet 5.5 was released on September 2026 and Claude Sonnet 4.5 on September 2025.