All Models
DeepSeek V3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Available Providers (21)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Nvidia | deepseek-ai/deepseek-v3.1 | $0.00/MTok | $0.00/MTok | 128K | 8.2K | |
 NanoGPT | deepseek-ai/DeepSeek-V3.1 | $0.20/MTok | $0.70/MTok | 128K | 65.5K | |
 submodel | deepseek-ai/DeepSeek-V3.1 | $0.20/MTok | $0.80/MTok | 75K | 163.8K | |
 OpenRouter | deepseek/deepseek-chat-v3.1 | $0.20/MTok | $0.80/MTok | 163.8K | 163.8K | |
 Jiekou.AI | deepseek/deepseek-v3.1 | $0.27/MTok | $1.00/MTok | 163.8K | 32.8K | |
 NovitaAI | deepseek/deepseek-v3.1 | $0.27/MTok | $1.00/MTok | 131.1K | 32.8K | |
 Meganova | deepseek-ai/DeepSeek-V3.1 | $0.27/MTok | $1.00/MTok | 164K | 164K | |
 Vercel AI Gateway | deepseek/deepseek-v3.1 | $0.30/MTok | $1.00/MTok | 163.8K | 128K | |
 Baseten | deepseek-ai/DeepSeek-V3.1 | $0.50/MTok | $1.50/MTok | 164K | 131K | |
 Abacus | deepseek/deepseek-v3.1 | $0.55/MTok | $1.66/MTok | 128K | 8.2K | |
 Weights & Biases | deepseek-ai/DeepSeek-V3.1 | $0.55/MTok | $1.65/MTok | 161K | 161K | |
 Fireworks AI | accounts/fireworks/models/deepseek-v3p1 | $0.56/MTok | $1.68/MTok | 163.8K | 163.8K | |
 Azure Cognitive Services | deepseek-v3.1 | $0.56/MTok | $1.68/MTok | 131.1K | 131.1K | |
 Synthetic | hf:deepseek-ai/DeepSeek-V3.1 | $0.56/MTok | $1.68/MTok | 128K | 128K | |
 LLM Gateway | deepseek-v3.1 | $0.56/MTok | $1.68/MTok | 128K | 32.8K | |
 Azure | deepseek-v3.1 | $0.56/MTok | $1.68/MTok | 131.1K | 131.1K | |
 Alibaba (China) | deepseek-v3-1 | $0.57/MTok | $1.72/MTok | 131.1K | 65.5K | |
 Amazon Bedrock | deepseek.v3-v1:0 | $0.58/MTok | $1.68/MTok | 163.8K | 81.9K | |
 Vertex | deepseek-ai/deepseek-v3.1-maas | $0.60/MTok | $1.70/MTok | 163.8K | 32.8K | |
 Together AI | deepseek-ai/DeepSeek-V3-1 | $0.60/MTok | $1.70/MTok | 131.1K | 131.1K | |
 Qiniu | deepseek-v3.1 | —/MTok | —/MTok | 128K | 32K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output