DEEPSEEK · TEXT MODEL
deepseek-v3.2 API access through TokenAAS
A DeepSeek language model listed for conversational, reasoning, and general text workloads through the TokenAAS compatible API.
- Chat assistants
- Reasoning
- Content generation
- Unified endpoint: /v1/chat/completions
- Billing: per million input and output tokens
Frequently asked questions
How do I call deepseek-v3.2 through TokenAAS?
Create a TokenAAS API key and send the model name deepseek-v3.2 to the /v1/chat/completions endpoint.
How is deepseek-v3.2 usage billed?
Usage is billed per million input and output tokens. The live model catalog shows the currently configured TokenAAS rate.
Is deepseek-v3.2 always available?
Availability is capacity-aware and may change. Check the live model catalog before production use and implement retry or fallback handling.