Home › Compare › Claude Sonnet 5 vs Claude Sonnet 5.5
Claude Sonnet 5 vs Claude Sonnet 5.5
A straight cost comparison of Claude Sonnet 5 (Anthropic) and Claude Sonnet 5.5 (Anthropic), per 1,000,000 tokens, verified November 2026.
Rate-by-rate comparison
| Metric | Claude Sonnet 5 | Claude Sonnet 5.5 | Winner |
|---|---|---|---|
| Input / 1M | $2 | $2 | Tie |
| Cached input / 1M | $0.20 | $0.10 | Claude Sonnet 5.5 |
| Cache write / 1M | $2.50 | $2.50 | Tie |
| Output / 1M | $10 | $10 | Tie |
| Context window | 1,000,000 | 1,000,000 | Tie |
| Batch API | Yes | Yes | Tie |
| Long-context tier | None | None | — |
For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.
Blended cost: 1M input + 250K output
| Model | Blended cost | Difference |
|---|---|---|
| Claude Sonnet 5 | $4.50 | Tie |
| Claude Sonnet 5.5 | $4.50 | Tie |
Ten workloads, two bills
The same two models, priced across ten workloads that differ only in their input:output ratio. Nothing else changes — no retries, no system prompt, no middleware.
| Workload | Claude Sonnet 5 | Claude Sonnet 5.5 | Winner |
|---|---|---|---|
| Classification 100K reqs · 500 in / 10 out | $110 | $110 | Tie |
| Data extraction 10K reqs · 2K in / 200 out | $60 | $60 | Tie |
| Support chat 1K reqs · 4K in / 600 out | $14 | $14 | Tie |
| Code review 2K reqs · 8K in / 1.5K out | $62 | $62 | Tie |
| Summarisation 1K reqs · 20K in / 1K out | $50 | $50 | Tie |
| Agent loop 5K reqs · 12K in / 2K out | $220 | $220 | Tie |
| Translation 500 reqs · 15K in / 15K out | $90 | $90 | Tie |
| Long-document QA 200 reqs · 120K in / 800 out | $49.60 | $49.60 | Tie |
| Cached RAG 1K reqs · 50K in (45K cached) / 1K out | $29.10 | $24.61 | Claude Sonnet 5.5 |
| Nightly batch 10K reqs · 10K in / 2K out | $200 | $200 | Tie |
Claude Sonnet 5 wins 0 of 10, Claude Sonnet 5.5 wins 1 of 10. The winner is set by the token mix, not by the headline rate.
Where the two bills cross over
Both models bill identical input and output rates, so there is no crossover: the two bills are equal at every ratio, and the choice rests entirely on context window, throughput and output quality.
Cost at four scales
The same support-chat workload (4K input, 600 output per request) at four monthly volumes.
| Requests / month | Claude Sonnet 5 | Claude Sonnet 5.5 | Difference |
|---|---|---|---|
| 100 | $1.40 | $1.40 | Tie |
| 1,000 | $14 | $14 | Tie |
| 10,000 | $140 | $140 | Tie |
| 100,000 | $1,400 | $1,400 | Tie |
What caching does to each bill
Caching only helps the part of the prompt that repeats. This is the support-chat workload (1,000 requests, 4,000 input tokens each) with an increasing share of that prompt served from a warm cache, written once on the first request.
| Cached share of the prompt | Claude Sonnet 5 | Claude Sonnet 5.5 | Winner |
|---|---|---|---|
| 0% | $14 | $14 | Tie |
| 50% | $10.40 | $10.20 | Claude Sonnet 5.5 |
| 80% | $8.25 | $7.93 | Claude Sonnet 5.5 |
| 95% | $7.17 | $6.79 | Claude Sonnet 5.5 |
Both models publish a cached-read rate, so the discount is comparable: Claude Sonnet 5 reads cache at $0.20 per million, Claude Sonnet 5.5 at $0.10.
Which one should you pick?
Claude Sonnet 5 wins on none of the ten workloads above, while Claude Sonnet 5.5 wins on cached rag.
Beyond price, the two differ on cached-input rate ($0.20 vs $0.10).
Batch mode is available on Claude Sonnet 5 and Claude Sonnet 5.5, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.
FAQ
Is Claude Sonnet 5 cheaper than Claude Sonnet 5.5?
No — they are priced identically at $4.50 on a blended 1M-input-plus-250K-output workload, with the same per-token rates. Choose on context window, throughput or output quality instead.
Which handles longer prompts, Claude Sonnet 5 or Claude Sonnet 5.5?
Both models share the same 1,000,000-token context window. Neither model publishes a long-context surcharge.
Do both models support prompt caching?
Claude Sonnet 5 bills cached reads at $0.20 per 1M; Claude Sonnet 5.5 at $0.10.
Related comparisons
- Claude Sonnet 5 vs Claude Haiku 4.5
- Claude Sonnet 5.5 vs Claude Sonnet 4.6
- GPT-6 Sol vs Claude Sonnet 5
- All Anthropic pricing
- All Anthropic pricing