Скорость вывода
9247.9 tok/s
9347.1 tok/s
94Claude Sonnet 4.647.0 tok/s
9546.9 tok/s
Claude Sonnet 4.6 by Anthropic is available through 201 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 4 providers. Context window: 1,000,000. In speed benchmarks, the fastest provider reaches 86 tok/s.
Anthropic Claude Sonnet 4.6 extends the Sonnet line with improved tool use, coding reliability, and long-context performance for everyday production workloads.
Также известна как
Compare Claude Sonnet 4.6 API pricing across 197 providers. Input prices range from $0.0004 to $29970.00 per million input. Crond offers the lowest rate at $0.0004/M. 4 providers offer free API credits or a free tier.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
哈基米API站100% | claude-sonnet-4-6 | — | $3.60 | $18.00 | 85.7 t/s+82% | 1.83 s |
KZW API100% | claude-sonnet-4-6 | — | $3.00 | $15.00 | 48.7 t/s+3% | 1.94 s |
Fucheers99.3% | claude-sonnet-4-6 | 64100100100 | $0.411-86% | $2.05-86% | 47.8 t/s+2% | 0.72 s-44% |
Tokeness99.9% | claude-sonnet-4-6 | 598484100 | $1.95-35% | $9.75-35% | 47.0 t/s | 1.59 s |
ApiToken Online82.4% | claude-sonnet-4-6 | 6968100100 | $73.00 | $365.00 | 46.2 t/s | 3.19 s |
Aitoke99.9% | claude-sonnet-4-6 | — | $0.411-86% | $2.05-86% | 43.1 t/s | 2.40 s |
ModelPool97.7% | claude-sonnet-4-6 | — | $0.257-91% | $1.29-91% | 40.9 t/s | 3.71 s |
MIXAPI-3.3100% | claude-sonnet-4-6 | — | $75.00 | $375.00 | 37.7 t/s | 3.07 s |
UoCode99.9% | claude-sonnet-4-6 | — | $0.411-86% | $2.05-86% | 31.9 t/s | 6.07 s |
小水管 API100% | claude-sonnet-4-6 | 5375100100 | Бесплатно | Бесплатно | 30.6 t/s | 4.12 s |
EasyMore99.9% | claude-sonnet-4-6 | — | $3.00 | $15.00 | 26.8 t/s | 11.92 s |
速创API99.9% | claude-sonnet-4-6 | — | $3.00 | $15.00 | 19.7 t/s | 8.43 s |
柏拉图AI100% | claude-sonnet-4-6 | — | $0.411-86% | $2.05-86% | — | — |
V-API100% | claude-sonnet-4-6 | — | $3.00 | $15.00 | — | — |
| claude-sonnet-4-6-high | — | $3.00 | $15.00 | — | — | |
| claude-sonnet-4-6-low | — | $3.00 | $15.00 | — | — | |
| claude-sonnet-4-6-medium | — | $3.00 | $15.00 | — | — | |
老张API100% | claude-sonnet-4-6 | — | $2.88-4% | $14.38-4% | — | — |
PackyAPI100% | claude-sonnet-4-6 | 727280100 | $0.429-86% | $2.14-86% | — | — |
Cuz AI100% | claude-sonnet-4-6 | — | $3.00 | $15.00 | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
哈基米API站 claude-sonnet-4-6 | 85.69 tok/s | 1.83s | 10 |
claude-sonnet-4-6 | 62.04 tok/s | 5.36s | 10 |
claude-sonnet-4-6 | 55.16 tok/s | 2.09s | 5 |
[按量]anti/claude-sonnet-4-6 | 49.13 tok/s | 8.19s | 5 |
claude-sonnet-4-6 | 48.66 tok/s | 1.94s | 5 |
claude-sonnet-4-6 | 47.77 tok/s | 0.72s | 5 |
claude-sonnet-4-6 | 47.04 tok/s | 1.59s | 5 |
claude-sonnet-4-6 | 46.71 tok/s | 1.07s | 5 |
claude-sonnet-4-6 | 46.15 tok/s | 3.19s | 5 |
claude-sonnet-4-6 | 43.57 tok/s | 1.12s | 5 |
claude-sonnet-4-6 | 43.13 tok/s | 2.40s | 5 |
claude-sonnet-4-6 | 42.40 tok/s | 4.58s | 5 |
claude-sonnet-4-6 | 40.85 tok/s | 3.71s | 10 |
anthropic/claude-sonnet-4.6 | 39.82 tok/s | 3.15s | 25 |
claude-sonnet-4-6 | 38.62 tok/s | 5.72s | 12 |
claude-sonnet-4-6 | 37.66 tok/s | 3.07s | 5 |
claude-sonnet-4-6 | 31.88 tok/s | 6.07s | 25 |
claude-sonnet-4-6 | 30.62 tok/s | 4.12s | 10 |
claude-sonnet-4-6 | 26.82 tok/s | 11.92s | 5 |
claude-sonnet-4-6 | 19.71 tok/s | 8.43s | 5 |
Показано 1–20 из 20 провайдеров
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.
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.
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.
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.
claude-opus-4-7
Anthropic Claude Opus 4.7 targets frontier-level analysis, complex coding, and autonomous workflows that require deep multi-step reasoning.
Рейтинги основаны на тестах, предоставленных сообществом, и периодических зондах работоспособности. Носит рекомендательный характер, не является официальными данными.Artificial Analysis
