Compare Anthropic Claude Sonnet 4.5 with other AI models
See how Claude Sonnet 4.5 from Anthropic compares with other AI models on price, context length and features.
- Claude Sonnet 4.5 is deprecated.
- Claude Sonnet 4.5 is currently failing most requests on Oxyy.
1 model
Overview
| Metric | Claude Sonnet 4.5 |
|---|---|
| Author | Anthropic |
| Type | Text |
| Context length | 200K tokens |
| Max output | 64K tokens |
| Reasoning | Yes |
| Input modalities | TextImageFile |
| Output modalities | Text |
| Released | Sep 29, 2025 |
| Knowledge cutoff | January 2025 |
| Served by | Anthropic via Oxyy |
| API | OpenAI-compatible · Anthropic Messages/v1/chat/completions |
- Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.
Pricing
| Metric | Claude Sonnet 4.5 |
|---|---|
| Input | $1.20 /1M inputStandard $3.00 |
| Output | $6.00 /1M outputStandard $15.00 |
| Cached input | $0.120 /1M cachedStandard $0.300 |
| Cache write (5 min) | $1.50 /1M cache writeStandard $3.75 |
| Cache write (1 hour) | $2.40 /1M cache write 1hStandard $6.00 |
| Blended price (3:1 input:output) | $2.40 /1M tokens |
- Includes the Launch Promo discount (60% off the standard price).
Performance
| Metric | Claude Sonnet 4.5 |
|---|---|
| Latency (p50, 7 days) | 2.32 s |
| Time to first token (p50) | 1.90 s |
| Throughput (p50) | 190.5 tok/s |
| Tokens (7 days) | 1.7M |
Visualize performance
- Claude Sonnet 4.5
Features
| Metric | Claude Sonnet 4.5 |
|---|---|
| Tool use | Yes |
| Structured outputs | Yes |
| Prompt caching | Yes |
| Streaming | Yes |
| Web search | Yes |
| Image input | Yes |
Activity
| Metric | Claude Sonnet 4.5 |
|---|---|
| Tokens (30 days) | 15.9M tokens · last 30 days |
| Input tokens | 14.1M |
| Output tokens (excluding reasoning) | 1.8M |
| Reasoning tokens | 0 |
- Input 14.1M
- Output (excl. reasoning) 1.8M
- Reasoning 0
Suggested models to compare
How this comparison is built
Prices are what Oxyy charges today; where a discount applies, the standard price is shown beside it. Context window, output limit, modalities and features come from the Oxyy model catalog. Latency, time to first token and throughput are medians measured on Oxyy traffic over the last 7 days (throughput from streaming requests only); a model with too little traffic shows a dash. Benchmark scores appear only with their source and date. Oxyy is an independent API gateway, not affiliated with the model vendors named on this page.