deepseek-r1-distill-llama
Разработчик: DeepSeek
DeepSeek R1 Distill Llama is a distilled reasoning model based on Llama, bringing chain-of-thought style performance to open-weight deployments.
Также известна как
DeepSeek R1 Distill Llama by DeepSeek is available through 25 API providers on LMSpeed. Compare API pricing from $0.010 to $75.00 per million input tokens across providers. Free API access is offered by 1 provider. In speed benchmarks, the fastest provider reaches 49 tok/s.
Compare DeepSeek R1 Distill Llama API pricing across 24 providers. Input prices range from $0.010 to $75.00 per million input. 素墨API offers the lowest rate at $0.010/M. 1 provider offers free API credits or a free tier.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
MapleLeaf API100% | deepseek-ai/deepseek-r1-distill-llama-8b | — | $75.00 | $75.00 | — | — |
素墨API100% | deepseek-ai/deepseek-r1-distill-llama-8b | — | $0.010 | $0.010 | — | — |
| deepseek-r1-distill-llama-8b | — | $0.010 | $0.010 | — | — | |
Seamee API100% | deepseek-ai/DeepSeek-R1-Distill-Llama-70B | — | $0.030 | $0.110 | — | — |
| DeepSeek-R1-Distill-Llama-8B | — | $0.200 | $0.020 | — | — | |
| deepseek-ai/DeepSeek-R1-Distill-Llama-8B | — | $0.200 | $0.020 | — | — | |
钱多多 API100% | deepseek-r1-distill-llama-70b | — | $0.392 | $0.979 | — | — |
| deepseek-r1-distill-llama-8b | — | $0.392 | $1.57 | — | — | |
| deepseek-ai/DeepSeek-R1-Distill-Llama-70B | — | $0.979 | $2.94 | — | — | |
PoloAPI100% | deepseek-r1-distill-llama-8b | — | $0.274 | $0.822 | — | — |
IXIOCCAPI99.9% | Pro/deepseek-ai/DeepSeek-R1-Distill-Llama-8B | — | $1.00 | $0.500 | — | — |
| deepseek-ai/DeepSeek-R1-Distill-Llama-70B | — | $1.00 | $0.500 | — | — | |
| deepseek-ai/DeepSeek-R1-Distill-Llama-8B | — | $1.00 | $0.500 | — | — | |
| deepseek-r1-distill-llama-70b | — | $1.00 | $0.500 | — | — | |
| deepseek/deepseek-r1-distill-llama-70b | — | $1.00 | $0.500 | — | — | |
| deepseek/deepseek-r1-distill-llama-70b:free | — | $1.00 | $0.500 | — | — | |
| deepseek/deepseek-r1-distill-llama-8b | — | $1.00 | $0.500 | — | — | |
| ppinfra/deepseek/deepseek-r1-distill-llama-70b | — | $1.00 | $0.500 | — | — | |
| ppinfra/deepseek/deepseek-r1-distill-llama-8b | — | $1.00 | $0.500 | — | — | |
| DeepSeek-R1-Distill-Llama-70B | — | $75.00 | $75.00 | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
PPIO deepseek/deepseek-r1-distill-llama-8b | 49.35 tok/s | 1.03s | 5 |
deepseek-ai/DeepSeek-R1-Distill-Llama-70B | 27.80 tok/s | 29.05s | 29 |
deepseek-r1-distill-llama-70b | 24.65 tok/s | 23.28s | 15 |
deepseek-ai/DeepSeek-R1-Distill-Llama-70B | 22.56 tok/s | 6.14s | 1 |
deepseek/deepseek-r1-distill-llama-70b | 18.54 tok/s | 1.57s | 5 |
Показано 1–5 из 5 провайдеров
deepseek-v3-2
DeepSeek V3.2 is a large language model in the DeepSeek V3 series, offering advanced reasoning, code generation, and multimodal capabilities.
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-r1
DeepSeek R1 is a reasoning-focused language model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.
deepseek-v3-1
DeepSeek V3.1 is an open-weights style frontier model from DeepSeek with strong math, coding, and Chinese-English bilingual reasoning.
kimi-k2-5
Moonshot Kimi K2.5 is a large language model in the Kimi series, offering advanced reasoning, code generation, and multimodal capabilities.
deepseek-r1-distill-qwen
DeepSeek R1 Distill Qwen is a reasoning model in the DeepSeek series, distilling R1 capabilities into the Qwen architecture for complex reasoning and analytical tasks.
Рейтинги основаны на тестах, предоставленных сообществом, и периодических зондах работоспособности. Носит рекомендательный характер, не является официальными данными.
