DeepSeek V3.2 API via TokenMix
Use DeepSeek V3.2 from DeepSeek as a chat model through the TokenMix AI API relay and multi-model gateway.
DeepSeek V3.2 non-thinking mode. 671B MoE model (37B active) with 128K context. Excels at general chat, code generation, and agent tasks with integrated tool-use across 1,800+ environments.
API access
- Base URL:
https://api.tokenmix.ai/v1 - Model ID:
deepseek-v3.2 - OpenAI SDK compatible. Change the base URL and use your TokenMix API key.
Pricing
Input $0.264706/M tokens, output $0.397059/M tokens
Capabilities
Function calling, JSON mode, Streaming, Reasoning
Model specs
- Context: 128K tokens
- Max output: 32K tokens
Availability
5/5 available API endpoints are healthy right now.
Recent performance
TTFT 927ms, latency 6477ms, throughput 43.7 tok/s.
Start using this model
Create an API key, top up from $1 when needed, and call this model through the TokenMix OpenAI-compatible endpoint.