DeepSeek API
DeepSeek API access through an OpenAI-compatible gateway
EasyAI gives developers a single API surface for DeepSeek reasoning workloads. Keep the SDK and request shape you already use, then select the enabled DeepSeek model by name.
Use chat completions, streaming, tools, and JSON-style workflows where the enabled model supports them.
Keep one key and one balance while testing DeepSeek alongside other enabled models.
Check the live model catalog for the exact model ID, availability, and current rate.
Who this is for
Developers building structured extraction, internal automation, coding assistants, and agent workflows.
Get an API keyFrequently asked questions
What base URL should I use?
Use the EasyAI /v1 base URL shown in the Quickstart documentation and set the model to the DeepSeek ID returned by GET /v1/models.
Can I stream DeepSeek responses?
Use stream=true when the selected model and endpoint advertise streaming support. Follow the compatibility notes for current behavior.
Where do I find the current DeepSeek price?
Use the EasyAI pricing page and model detail page. Rates are live reference values and can vary by account group.