Рассуждение
MMLU-Pro5974.4%
6074.2%
62DeepSeek R1 Distill Qwen73.9%
6372.4%
DeepSeek R1 Distill Qwen by DeepSeek is available through 70 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 5 providers. Context window: 128,000. In speed benchmarks, the fastest provider reaches 92 tok/s.
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.
Также известна как
Compare DeepSeek R1 Distill Qwen API pricing across 65 providers. Input prices range from $0.010 to $75.00 per million input. AAAI offers the lowest rate at $0.010/M. 5 providers offer free API credits or a free tier.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
V-API100% | DeepSeek-R1-Distill-Qwen-7B | — | $0.010 | $0.010 | — | — |
| DeepSeek-R1-Distill-Qwen-14B | — | $0.015 | $0.015 | — | — | |
| DeepSeek-R1-Distill-Qwen-32B | — | $0.020 | $0.020 | — | — | |
小水管 API100% | deepseek-r1-distill-qwen-14b | — | Бесплатно | Бесплатно | — | — |
| deepseek-r1-distill-qwen-7b | — | Бесплатно | Бесплатно | — | — | |
Cuz AI100% | deepseek-r1-distill-qwen-32b | — | $0.287 | $0.861 | — | — |
天絮 API100% | deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | — | $2.86 | $2.86 | — | — |
初叶🍂Furry API98.1% | deepseek-r1-distill-qwen-14b | — | $0.050 | $0.050 | — | — |
| deepseek-r1-distill-qwen-32b | — | $0.050 | $0.050 | — | — | |
| deepseek-r1-distill-qwen-7b | — | $0.050 | $0.050 | — | — | |
AAAI100% | DeepSeek-R1-Distill-Qwen-7B | — | $0.010 | $0.010 | — | — |
| DeepSeek-R1-Distill-Qwen-14B | — | $0.015 | $0.015 | — | — | |
| DeepSeek-R1-Distill-Qwen-32B | — | $0.020 | $0.020 | — | — | |
素墨API100% | deepseek-ai/deepseek-r1-distill-qwen-14b | — | $0.010 | $0.010 | — | — |
| deepseek-ai/deepseek-r1-distill-qwen-32b | — | $0.010 | $0.010 | — | — | |
| deepseek-ai/deepseek-r1-distill-qwen-7b | — | $0.010 | $0.010 | — | — | |
| deepseek-r1-distill-qwen-14b | — | $0.010 | $0.010 | — | — | |
| deepseek-r1-distill-qwen-32b | — | $0.010 | $0.010 | — | — | |
| deepseek-r1-distill-qwen-7b | — | $0.010 | $0.010 | — | — | |
Seamee API100% | deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | — | $0.100 | $0.100 | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
阿里云百炼 DashScope deepseek-r1-distill-qwen-7b | 92.17 tok/s | 9.98s | 5 |
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | 68.62 tok/s | 9.89s | 40 |
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | 67.68 tok/s | 10.66s | 5 |
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | 44.58 tok/s | 32.11s | 15 |
deepseek-ai/deepseek-r1-distill-qwen-14b | 40.96 tok/s | 0.49s | 5 |
deepseek/deepseek-r1-distill-qwen-14b | 39.94 tok/s | 1.25s | 5 |
deepseek-r1-distill-qwen-32b | 36.48 tok/s | 42.23s | 15 |
deepseek-ai/deepseek-r1-distill-qwen-32b | 33.97 tok/s | 0.59s | 5 |
deepseek-r1-distill-qwen-32b-250120 | 26.05 tok/s | 35.46s | 10 |
deepseek/deepseek-r1-distill-qwen-32b | 22.32 tok/s | 1.17s | 5 |
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | 11.53 tok/s | 60.01s | 5 |
Показано 1–11 из 11 провайдеров
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.
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.
minimax-m2-5
MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
qwen3
Alibaba Qwen3 is the Qwen family's flagship LLM series with dense and MoE variants, seamless thinking/non-thinking modes, and leading open-source performance in math, code, and agent tasks.
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
Рейтинги основаны на тестах, предоставленных сообществом, и периодических зондах работоспособности. Носит рекомендательный характер, не является официальными данными.Artificial Analysis
