Цена входных данных
30$1.25/M
30$1.25/M
31DeepSeek R1$1.35/M
32$1.40/M
DeepSeek R1 by DeepSeek is available through 163 API providers on LMSpeed. Compare API pricing from $0.0010 to $547.50 per million input tokens across providers. Free API access is offered by 2 providers. Context window: 163,840. In speed benchmarks, the fastest provider reaches 241 tok/s.
DeepSeek R1 is a reasoning-focused language model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.
Также известна как
Compare DeepSeek R1 API pricing across 161 providers. Input prices range from $0.0010 to $547.50 per million input. 10dian-API offers the lowest rate at $0.0010/M. 2 providers offer free API credits or a free tier.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
丸美小沐99.8% | deepseek-r1 | — | $75.00 | $75.00 | 25.9 t/s | 5.73 s |
老张API100% | deepseek-r1 | — | $0.547-60% | $2.19-48% | — | — |
| deepseek-r1-0528 | — | $0.547-60% | $2.19-48% | — | — | |
| deepseek-r1-250528 | — | $0.547-60% | $2.19-48% | — | — | |
柏拉图AI100% | deepseek-r1 | — | $0.548-59% | $2.19-48% | — | — |
V-API100% | deepseek-r1-0528 | — | $4.00 | $16.00 | — | — |
MapleLeaf API100% | deepseek-ai/deepseek-r1 | — | Бесплатно | Бесплатно | — | — |
| deepseek-ai/deepseek-r1-0528 | — | Бесплатно | Бесплатно | — | — | |
| deepseek-r1 | — | $0.400-70% | $1.70-60% | — | — | |
| deepseek-r1-250528 | — | $75.00 | $75.00 | — | — | |
天絮 API100% | Pro/deepseek-ai/DeepSeek-R1 | — | $3.57 | $15.57 | — | — |
| deepseek-ai/DeepSeek-R1 | — | $21.43 | $50.00 | — | — | |
6345ywz API99.8% | deepseek/deepseek-r1-0528 | — | $0.062-95% | $0.295-93% | — | — |
| Pro/deepseek-ai/DeepSeek-R1 | — | $0.068-95% | $0.299-93% | — | — | |
| deepseek/deepseek-r1-32b | — | $0.137-90% | $0.685-84% | — | — | |
| deepseek/deepseek-r1-70b | — | $0.137-90% | $0.685-84% | — | — | |
| deepseek-ai/DeepSeek-R1 | — | $0.411-70% | $0.959-77% | — | — | |
初叶🍂Furry API98.1% | deepseek-r1 | — | $0.050-96% | $0.050-99% | — | — |
| siliconflow/deepseek-r1-0528 | — | $0.050-96% | $0.050-99% | — | — | |
| vanchin/deepseek-r1 | — | $0.050-96% | $0.050-99% | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
钠 API deepseek-ai/DeepSeek-R1-0528-fast | 240.66 tok/s | 1.34s | 5 |
deepseek-r1:1.5b | 217.41 tok/s | 0.52s | 5 |
deepseek-ai/DeepSeek-R1 | 217.38 tok/s | 0.53s | 4 |
deepseek-r1:7b | 111.66 tok/s | 9.09s | 120 |
deepseek-r1:7b | 109.50 tok/s | 13.15s | 5 |
deepseek-ai/deepseek-r1 | 106.80 tok/s | 7.66s | 5 |
deepseek-ai/DeepSeek-R1 | 103.70 tok/s | 2.24s | 13 |
deepseek-ai/deepseek-r1 | 87.63 tok/s | 8.96s | 15 |
deepseek-ai/DeepSeek-R1 | 75.52 tok/s | 30.69s | 74 |
deepseek-r1 | 74.64 tok/s | 1.58s | 3 |
deepseek/deepseek-r1 | 66.19 tok/s | 6.29s | 52 |
deepseek/deepseek-r1-70b | 63.75 tok/s | 5.27s | 30 |
deepseek-r1 | 56.00 tok/s | 1.50s | 5 |
deepseek/deepseek-r1-32b | 54.18 tok/s | 4.46s | 30 |
deepseek-r1 | 49.94 tok/s | 2.87s | 5 |
deepseek/deepseek-r1-0528 | 48.55 tok/s | 11.41s | 72 |
deepseek-r1:7b | 46.77 tok/s | 5.66s | 385 |
deepseek-ai/DeepSeek-R1-0528 | 46.73 tok/s | 15.23s | 30 |
deepseek/deepseek-r1-0528:free | 45.66 tok/s | 13.57s | 10 |
TA/deepseek-ai/DeepSeek-R1 | 45.10 tok/s | 2.29s | 5 |
Показано 1–20 из 47 провайдеров
deepseek-v3
DeepSeek V3 is DeepSeek flagship MoE language model with 671B total parameters, delivering strong performance in reasoning, coding, and multilingual tasks at competitive inference cost.
deepseek-v3-2
DeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
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.
glm-5
Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.
Рейтинги основаны на тестах, предоставленных сообществом, и периодических зондах работоспособности. Носит рекомендательный характер, не является официальными данными.Artificial Analysis
