Free DeepSeek API - 111 Models, Compare Speed & Latency

Model	Providers	Speed	Latency	Tests
kiro-deepseek-3-2-agenticDeepSeekFree	TommyLam API	N/A	N/A	0
deepseek-v4-pro[cc]DeepSeekFree Claude Code	Dibin84 API Hub	N/A	N/A	0
deepseek-v4-flash[cc]DeepSeekFree Claude Code	Dibin84 API Hub	N/A	N/A	0
[F]deepseek-v4-proDeepSeekFree		N/A	N/A	0
[NV]deepseek-v4-flashDeepSeekFree		N/A	N/A	0
[NV]deepseek-v4-proDeepSeekFree		N/A	N/A	0
[D]DeepSeek-V4-FlashDeepSeekFree		N/A	N/A	0
[q]deepseek-v4-proDeepSeekFree		N/A	N/A	0
[D]DeepSeek-V3.2DeepSeekFree		N/A	N/A	0
[q]deepseek-v4-flashDeepSeekFree		N/A	N/A	0
[D]DeepSeek-V4-Pro[128k]DeepSeekFree		N/A	N/A	0
deepseek-ai/deepseek-r1-distill-qwen-7bDeepSeekFree		N/A	N/A	0
deepseek-ai/deepseek-r1-distill-llama-8bDeepSeekFree		N/A	N/A	0
deepseek-ai/deepseek-r1-distill-qwen-14bDeepSeekFree		N/A	N/A	0
deepseek-ai/deepseek-r1-distill-qwen-32bDeepSeekFree		N/A	N/A	0
deepseek-freeDeepSeekFree		N/A	N/A	0
tngtech/deepseek-r1t2-chimeraDeepSeekFree		N/A	N/A	0
nex-agi/deepseek-v3.1-nex-n1DeepSeekFree		N/A	N/A	0
DeepSeekFree ReasoningTools1MOpen WeightsDeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.	+45 moreShow fewer	42.34 t/s	13.36 s	20
DeepSeekFree 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.	+50 moreShow fewer	82.51 t/s	9.99 s	30
deepseek-r1-distill-qwen-14bAlibaba (China)Free ReasoningTools32.8K		N/A	N/A	0
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B阿里巴巴Free		N/A	N/A	0
deepseek-ai/DeepSeek-R1-Distill-Qwen-32BSiliconFlow (China)Free ReasoningTools131K		N/A	N/A	0
deepseek-ai/DeepSeek-R1-Distill-Qwen-14BSiliconFlow (China)Free ReasoningTools131K		N/A	N/A	0
deepseek-r1-distill-qwen-32bVultrFree ReasoningToolsOpen Weights121.8K		N/A	N/A	0
deepseek-r1-distill-qwen-1.5bDeepSeekFree		N/A	N/A	0
APEX-deepseek-v3.2-chatDeepSeekFree		N/A	N/A	0
APEX-deepseek-r1DeepSeekFree		N/A	N/A	0
APEX-deepseek-v3DeepSeekFree		N/A	N/A	0
deepseek-v3.2-agent(次模型)DeepSeekFree		N/A	N/A	0
deepseek-v3.1-terminus-agent(次模型)DeepSeekFree		N/A	N/A	0
APEX-deepseek-v3.1DeepSeekFree		N/A	N/A	0
APEX-deepseek-v3.2DeepSeekFree		N/A	N/A	0
APEX-deepseek-v3.2-reasonerDeepSeekFree		N/A	N/A	0
DeepSeekFree DeepSeek V4 is DeepSeek's next-generation foundation model family, built for advanced reasoning, coding, math, and long-context agent applications.		N/A	N/A	0
DeepSeekFree DeepSeek R1 Distill Qwen 1.5B is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.		N/A	N/A	0
DeepSeekFree DeepSeek V2.5 is a language model in the DeepSeek series, offering general-purpose reasoning, code generation, and multimodal capabilities.		N/A	N/A	0
DeepSeekFree ReasoningTools128KChatDeepSeek V3.1 is an open-weights style frontier model from DeepSeek with strong math, coding, and Chinese-English bilingual reasoning.	+18 moreShow fewer	N/A	N/A	0
DeepSeekFree DeepSeek V3 Turbo is a throughput-optimized DeepSeek V3 tier for large-scale chat, coding assistance, and MoE inference with strong price-to-performance.		N/A	N/A	0
DeepSeekFree DeepSeek R1 Turbo is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.		N/A	N/A	0
DeepSeekFree DeepSeek V3.2 Reasoner is a reasoning model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.		N/A	N/A	0
DeepSeekFree DeepSeek Coder Instruct is a code-specialized variant in the DeepSeek series, optimized for code generation, debugging, and software development tasks.	+2 moreShow fewer	N/A	N/A	0
DeepSeekFree FilesOpen WeightsVision8.2KDeepSeek OCR is an OCR model, specialized in extracting and understanding text from images and documents.	+8 moreShow fewer	N/A	N/A	0
DeepSeekFree DeepSeek Coder is a code-specialized language model in the DeepSeek series, optimized for code generation, completion, and software development tasks.	+1 moreShow fewer	N/A	N/A	0
DeepSeekFree 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.	+24 moreShow fewer	26.71 t/s	3.41 s	5
DeepSeekFree 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.	+35 moreShow fewer	36.08 t/s	1.40 s	5
DeepSeekFree ReasoningTools128K164KDeepSeek V3.1 Terminus is a Terminus-branded DeepSeek V3.1 variant tuned for stable long-context reasoning and code generation.	+15 moreShow fewer	N/A	N/A	0
DeepSeekFree DeepSeek Chat V3.1 is an instruction-tuned variant in the DeepSeek series, optimized for following instructions and conversational tasks.		N/A	N/A	0
DeepSeekFree 128KReasoningOpen Weights163.8KDeepSeek R1 is a reasoning-focused language model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.	+22 moreShow fewer	25.85 t/s	5.73 s	10
DeepSeekFree 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 moreShow fewer	N/A	N/A	0
DeepSeekFree 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...		N/A	N/A	0

Other Model Families