DeepSeek models
14 DeepSeek models you can call through UberLLM’s OpenAI-compatible API. The cheapest is DeepSeek V4.1 Flash at $0.0000/1M input tokens, as of October 24, 2026. Every request is routed to the cheapest healthy seller; the price shown includes UberLLM’s 10% fee.
| Model | Price (from) | Context | Type | Capabilities |
|---|---|---|---|---|
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | $0.0040 in · $0.0080 out | 1049K | Text | ToolsReasoningJSON |
| DeepSeek R1 deepseek/deepseek-r1 | 164K | Text | ToolsReasoning | |
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.0011 in · $0.0022 out | 1049K | Text | ToolsReasoningJSON |
| DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.0029 in · $0.0043 out | 164K | Text | ToolsReasoningJSON |
| DeepSeek V4 Flash (Morpheus Web) deepseek/deepseek-v4-flash:web | $0.1253 in · $0.2580 out | 1000K | Text | ToolsReasoningJSON |
| DeepSeek V4 Pro (Morpheus Web) deepseek/deepseek-v4-pro:web | $1.43 in · $3.13 out | 1000K | Text | ToolsReasoningJSON |
| DeepSeek V4 Flash E2EE deepseek/e2ee-deepseek-v4-flash | $0.1573 in · $0.3223 out | 1000K | Text | ToolsReasoning |
| DeepSeek V3.1 deepseek/deepseek-v3.1 | $0.0027 in · $0.0103 out | 128K | Text | ToolsJSON |
| DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.0010 in · $0.0020 out | 1049K | Text | ToolsReasoningJSON |
| DeepSeek V4 Flash 0731 Fast deepseek/deepseek-v4-flash-0731-fast | $0.2873 in · $0.5746 out | 1000K | Text | ToolsReasoningJSON |
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.0358 in · $0.1073 out | 1049K | Text | ToolsReasoningJSON |
| DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.0000 in · $0.0017 out | 1049K | Text | ToolsReasoningVisionJSON |
| DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0131 in · $0.0523 out | 1049K | Text | ToolsReasoningVisionJSON |
| DeepSeek V4.1 Flash Uncensored deepseek/deepseek-v4.1-flash-uncensored | $0.1650 in · $0.6600 out | 1049K | Text | Tools |
Compare DeepSeek models
DeepSeek models — FAQ
What is the cheapest DeepSeek model?
DeepSeek V4.1 Flash is the cheapest DeepSeek model on UberLLM right now, at $0.0000/1M input tokens. UberLLM routes each request to the cheapest healthy seller and bills the price shown, which includes UberLLM's 10% fee.
How many DeepSeek models can I use through UberLLM?
14 DeepSeek models are on the UberLLM marketplace today. One OpenAI-compatible API key and base URL (https://api.uberllm.dev/v1) calls every one of them — no per-provider contracts.
How do I call a DeepSeek model with the API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM key, and the model id (for example "deepseek/deepseek-v4-flash"). Anthropic SDKs work against https://api.uberllm.dev/v1/messages.