Claude Sonnet 4.5 by Anthropic is available through 162 API providers on LMSpeed. Compare API pricing from $0.0004 to $29970.00 per million input tokens across providers. Free API access is offered by 2 providers. Context window: 1,000,000. In speed benchmarks, the fastest provider reaches 126 tok/s.
Anthropic Claude Sonnet 4.5 balances strong reasoning, coding, and agent capabilities with lower latency and cost than Opus, making it a practical default for production assistants.
Также известна как
Compare Claude Sonnet 4.5 API pricing across 160 providers. Input prices range from $0.0004 to $29970.00 per million input. Crond offers the lowest rate at $0.0004/M. 2 providers offer free API credits or a free tier.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
天宫造物100% | claude-sonnet-4-5-20250929 | — | $3.00 | $15.00 | 45.4 t/s | 3.17 s |
CodeXE100% | claude-sonnet-4.5 | 728410088 | $0.050-98% | $0.050-100% | 44.4 t/s | 2.52 s |
EasyMore99.9% | claude-sonnet-4-5 | — | $3.00 | $15.00 | 28.8 t/s | 9.80 s |
| claude-sonnet-4-5-20250929 | — | $2.99 | $14.96 | — | — | |
柏拉图AI100% | claude-sonnet-4-5-20250929 | — | $0.411-86% | $2.05-86% | — | — |
V-API100% | claude-sonnet-4-5-20250929 | — | $3.00 | $15.00 | — | — |
老张API100% | claude-sonnet-4-5-20250929 | — | $2.88-4% | $14.38-4% | — | — |
PackyAPI100% | claude-sonnet-4-5-20250929 | — | $0.429-86% | $2.14-86% | — | — |
MapleLeaf API100% | claude-sonnet-4.5 | — | Бесплатно | Бесплатно | — | — |
AiXiaobai API100% | claude-sonnet-4-5-20250929 | — | $0.699-77% | $3.49-77% | — | — |
速创API99.9% | claude-sonnet-4-5-20250929 | — | $3.00 | $15.00 | — | — |
Leonhard API99.8% | claude-sonnet-4.5 | 64100100100 | $3.00 | $15.00 | — | — |
ApiToken Online82.4% | claude-sonnet-4-5-20250929 | — | $72.81 | $364.03 | — | — |
| claude-sonnet-4-5 | 7610010088 | $73.00 | $365.00 | — | — | |
Seamee API100% | claude-sonnet-4.5 | — | Бесплатно | Бесплатно | — | — |
| claude-sonnet-4-5-20250929 | — | $0.430-86% | $2.15-86% | — | — | |
UnifyLLM100% | claude-sonnet-4-5-20250929-c | — | $0.080-97% | $0.080-99% | — | — |
OpenRouter Fans100% | claude-sonnet-4-5-20250929 | — | $0.430-86% | $2.15-86% | — | — |
GuaiHub100% | claude-sonnet-4-5-20250929 | — | $0.370-88% | $1.85-88% | — | — |
TradingBase API100% | claude-sonnet-4-5-20250929 | — | $3.20 | $15.99 | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
包子铺 claude-sonnet-4-5-20250929 | 125.92 tok/s | 1.27s | 5 |
claude-sonnet-4.5 | 46.48 tok/s | 5.11s | 15 |
claude-sonnet-4-5 | 45.99 tok/s | 1.35s | 5 |
claude-sonnet-4-5-20250929 | 45.40 tok/s | 3.17s | 10 |
claude-sonnet-4.5 | 44.41 tok/s | 2.52s | 5 |
claude-sonnet-4-5-20250929 | 41.39 tok/s | 3.27s | 10 |
claude-sonnet-4.5 | 40.77 tok/s | 3.28s | 5 |
claude-sonnet-4-5 | 28.83 tok/s | 9.80s | 5 |
claude-sonnet-4.5 | 20.95 tok/s | 1.08s | 5 |
claude-sonnet-4-5-20250929 | 16.92 tok/s | 9.74s | 12 |
claude-sonnet-4-5-20250929 | 6.99 tok/s | 4.09s | 5 |
Показано 1–11 из 11 провайдеров
claude-haiku-4-5
Anthropic Claude Haiku 4.5 delivers fast, low-cost responses while retaining solid instruction following for chat, classification, and lightweight coding.
claude-sonnet-4-6
Anthropic Claude Sonnet 4.6 extends the Sonnet line with improved tool use, coding reliability, and long-context performance for everyday production workloads.
claude-opus-4-6
Anthropic Claude Opus 4.6 is the most capable Claude Opus tier, optimized for complex analysis, long-horizon coding, and high-stakes enterprise reasoning workloads.
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
gpt-5-2
OpenAI GPT-5.2 is a GPT-5 series model emphasizing advanced reasoning, multimodal understanding, and high-quality outputs for complex enterprise workloads.
gpt-5-3-codex
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
Рейтинги основаны на тестах, предоставленных сообществом, и периодических зондах работоспособности. Носит рекомендательный характер, не является официальными данными.Artificial Analysis