Providers & pricing
| Provider | Input | Output | Free tier |
|---|---|---|---|
 DeepSeek Default | 527.2 RODI/M~0.660 USD/M | 1581.6 RODI/M | — |
 Azure | 497.4 RODI/M~0.660 USD/M | 1492.0 RODI/M | — |
Pricing
| Rate | RODI | USD (ref.) | Unit |
|---|---|---|---|
| In | 527.2 | ~ 0.660 | USD/M · RODI/M |
| Out | 1581.6 | ~ 1.98 | USD/M · RODI/M |
| Cached | 17.6 | ~ 0.0220 | USD/M · RODI/M |
Tax +6%
Provider tax applied by the platform (China). The RODI rates above already include it.
RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.
Capabilities
Streaming
Tool calling
Vision
JSON mode
Reasoning
About this model
DeepSeek V4 Pro via Microsoft Foundry on Azure. Azure azure_ai/DeepSeek-V4-Pro. Most capable DeepSeek V4 MoE model with 1M context; supports non-thinking and thinking modes (thinking default), tool calls, and JSON output.
API usage
Use the canonical slug with client.chat() or chat.completions.create().
RodiumAi SDK
Official Python, JavaScript, and Laravel SDKs — flat API aligned with this model slug.
…Compatible SDKs (OpenAI / Anthropic packages)
…