DeepSeek
About DeepSeek
深度求索(DeepSeek),探索未至之境。专注于研究世界领先的通用人工智能底层模型与技术,开源 DeepSeek-V4、DeepSeek-R1 等前沿大模型。和 DeepSeek AI 对话,轻松接入 API。
Website ↗GitHub ↗
Source ↗ · 2026-11-12T02:17:03.411506080ZTransparency & Governance
- Foundation Model Transparency Index 2025 · 32 / 100 · Company disclosure assessment Source assessment ↗
101 indexed models
101 matching models
vercelAIGatewayCatalog/deepseek/deepseek-v4.1-flash-fast
Higher-throughput variant of DeepSeek V4.1 Flash for responsive coding, reasoning, and agentic workloads.
- Context window
- 1,048,576
- Maximum output
- 32,768
- Input modalities
- text, image
- Output modalities
- text
cheaperInference/deepseek-v4-flash
- Context window
- 1,000,000
- Maximum output
- 384,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs, toolCalling
cheaperInference/deepseek-v4-flash-0731
- Context window
- 1,048,576
- Maximum output
- 393,216
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs, toolCalling
azureFoundry/azureml-deepseek/DeepSeek-V4-Flash-0731@2026-07-31
DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities.
- Context window
- 1,000,000
- Maximum output
- 128,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- toolCalling
azureFoundry/azureml-deepseek/DeepSeek-V4-Flash@2024-04-23
DeepSeek V4 is an efficient MoE model family with 1M context and near state-of-the-art open-source reasoning performance.
- Context window
- 1,000,000
- Maximum output
- 128,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- toolCalling
azureFoundry/azureml-deepseek/DeepSeek-V4-Flash@2026-04-23
DeepSeek V4 is an efficient MoE model family with 1M context and near state-of-the-art open-source reasoning performance.
- Context window
- 1,000,000
- Maximum output
- 128,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- toolCalling
cheaperInference/deepseek-v4-flash-vision-exp
- Context window
- 1,048,576
- Maximum output
- 1,048,576
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, structuredOutputs, toolCalling, visionInput
Inference prices
cheaperInference/deepseek-v4-pro
- Context window
- 1,000,000
- Maximum output
- 1,048,600
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs, toolCalling
cheaperInference/deepseek-v4-pro-0813
- Context window
- 1,048,576
- Maximum output
- 393,216
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs, toolCalling, webSearch
azureFoundry/azureml-deepseek/DeepSeek-V4-Pro@2026-04-23
DeepSeek V4 is an efficient MoE model family with 1M context and near state-of-the-art open-source reasoning performance.
- Context window
- 1,000,000
- Maximum output
- 128,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
vertexAI/publishers/deepseek-ai/models/deepseek-r1@deepseek-r1-0528-fp4
- Input modalities
- text
- Output modalities
- text