GitHub

Модель	Провайдеры	Скорость	Задержка	Тестов
[D]DeepSeek-V3.2DeepSeekБесплатно	Soul 公益站	Н/Д	Н/Д	0
[D]DeepSeek-V4-FlashDeepSeekБесплатно	Soul 公益站	Н/Д	Н/Д	0
[D]DeepSeek-V4-Pro[128k]DeepSeekБесплатно	Soul 公益站	Н/Д	Н/Д	0
[F]deepseek-v4-proDeepSeekБесплатно		Н/Д	Н/Д	0
[NV]deepseek-v4-flashDeepSeekБесплатно		Н/Д	Н/Д	0
[NV]deepseek-v4-proDeepSeekБесплатно		Н/Д	Н/Д	0
[q]deepseek-v4-flashDeepSeekБесплатно		Н/Д	Н/Д	0
deepseek-ai/deepseek-r1-distill-qwen-14bDeepSeekБесплатно		Н/Д	Н/Д	0
deepseek-freeDeepSeekБесплатно		Н/Д	Н/Д	0
deepseek-ai/deepseek-r1-distill-llama-8bDeepSeekБесплатно		Н/Д	Н/Д	0
deepseek-ai/deepseek-r1-distill-qwen-7bDeepSeekБесплатно		Н/Д	Н/Д	0
deepseek-ai/deepseek-r1-distill-qwen-32bDeepSeekБесплатно		Н/Д	Н/Д	0
tngtech/deepseek-r1t2-chimeraDeepSeekБесплатно		Н/Д	Н/Д	0
nex-agi/deepseek-v3.1-nex-n1DeepSeekБесплатно		Н/Д	Н/Д	0
DeepSeekБесплатно ReasoningTools1MOpen WeightsDeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.	+41 ещёСвернуть	42.34 т/с	13.36 с	20
DeepSeekБесплатно ReasoningTools1MOpen WeightsDeepSeek 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.	+46 ещёСвернуть	82.51 т/с	9.99 с	30
deepseek-ai/DeepSeek-R1-Distill-Qwen-32BSiliconFlow (China)Бесплатно ReasoningTools131K		Н/Д	Н/Д	0
deepseek-r1-distill-qwen-32bVultrБесплатно ReasoningToolsOpen Weights121.8K		Н/Д	Н/Д	0
deepseek-r1-distill-qwen-14bAlibaba (China)Бесплатно ReasoningTools32.8K		Н/Д	Н/Д	0
deepseek-r1-distill-qwen-1.5bDeepSeekБесплатно		Н/Д	Н/Д	0
deepseek-ai/DeepSeek-R1-Distill-Qwen-14BSiliconFlow (China)Бесплатно ReasoningTools131K		Н/Д	Н/Д	0
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B阿里巴巴Бесплатно		Н/Д	Н/Д	0
deepseek-v3.1-terminus-agent(次模型)DeepSeekБесплатно		Н/Д	Н/Д	0
APEX-deepseek-v3DeepSeekБесплатно		Н/Д	Н/Д	0
APEX-deepseek-v3.2-chatDeepSeekБесплатно		Н/Д	Н/Д	0
deepseek-v3.2-agent(次模型)DeepSeekБесплатно		Н/Д	Н/Д	0
APEX-deepseek-v3.2DeepSeekБесплатно		Н/Д	Н/Д	0
APEX-deepseek-v3.2-reasonerDeepSeekБесплатно		Н/Д	Н/Д	0
APEX-deepseek-v3.1DeepSeekБесплатно		Н/Д	Н/Д	0
APEX-deepseek-r1DeepSeekБесплатно		Н/Д	Н/Д	0
DeepSeekБесплатно DeepSeek V4 is DeepSeek's next-generation foundation model family, built for advanced reasoning, coding, math, and long-context agent applications.		Н/Д	Н/Д	0
DeepSeekБесплатно DeepSeek R1 Distill Qwen 1.5B is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.		Н/Д	Н/Д	0
DeepSeekБесплатно DeepSeek V2.5 is a language model in the DeepSeek series, offering general-purpose reasoning, code generation, and multimodal capabilities.		Н/Д	Н/Д	0
DeepSeekБесплатно ReasoningTools128KReasoningDeepSeek V3.1 is an open-weights style frontier model from DeepSeek with strong math, coding, and Chinese-English bilingual reasoning.	+17 ещёСвернуть	Н/Д	Н/Д	0
DeepSeekБесплатно DeepSeek V3 Turbo is a throughput-optimized DeepSeek V3 tier for large-scale chat, coding assistance, and MoE inference with strong price-to-performance.		Н/Д	Н/Д	0
DeepSeekБесплатно DeepSeek R1 Turbo is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.		Н/Д	Н/Д	0
DeepSeekБесплатно DeepSeek V3.2 Reasoner is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.		Н/Д	Н/Д	0
DeepSeekБесплатно DeepSeek Coder Instruct is a code-specialized variant in the DeepSeek series, optimized for code generation, debugging, and software development tasks.	+2 ещёСвернуть	Н/Д	Н/Д	0
DeepSeekБесплатно FilesOpen WeightsVision8.2KDeepSeek OCR is an OCR model, specialized in extracting and understanding text from images and documents.	+8 ещёСвернуть	Н/Д	Н/Д	0
DeepSeekБесплатно 文本DeepSeek Coder is a code-specialized language model in the DeepSeek series, optimized for code generation, completion, and software development tasks.	+1 ещёСвернуть	Н/Д	Н/Д	0
DeepSeekБесплатно 128KReasoningToolsOpen WeightsDeepSeek V3 is DeepSeek flagship MoE language model with 671B total parameters, delivering strong performance in reasoning, coding, and multilingual tasks at competitive inference cost.	+22 ещёСвернуть	26.71 т/с	3.41 с	5
DeepSeekБесплатно ReasoningTools163.8K164KDeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.	+34 ещёСвернуть	36.08 т/с	1.40 с	5
DeepSeekБесплатно ReasoningTools128K164KDeepSeek V3.1 Terminus is a Terminus-branded DeepSeek V3.1 variant tuned for stable long-context reasoning and code generation.	+15 ещёСвернуть	Н/Д	Н/Д	0
DeepSeekБесплатно DeepSeek Chat V3.1 is an instruction-tuned variant in the DeepSeek series, optimized for following instructions and conversational tasks.		Н/Д	Н/Д	0
DeepSeekБесплатно 128KReasoningOpen Weights163.8KDeepSeek R1 is a reasoning-focused language model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.	+21 ещёСвернуть	25.85 т/с	5.73 с	10
DeepSeekБесплатно ReasoningTools131KReasoningDeepSeek R1 Distill Qwen is a reasoning model in the DeepSeek series, distilling R1 capabilities into the Qwen architecture for complex reasoning and analytical tasks.	+9 ещёСвернуть	Н/Д	Н/Д	0
DeepSeekБесплатно DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...		Н/Д	Н/Д	0

Бесплатный DeepSeek API

Другие семейства моделей