DeepSeek V3.1 Terminus API via TokenMix
Use DeepSeek V3.1 Terminus from DeepSeek as a chat model through the TokenMix AI API relay and multi-model gateway.
Refined version of V3.1 incorporating user feedback. 671B MoE model with improved language consistency, stronger code/search agent performance, and more stable outputs. Open-weight on Hugging Face.
API access
- Base URL:
https://api.tokenmix.ai/v1 - Model ID:
deepseek-v3.1-terminus - OpenAI SDK compatible. Change the base URL and use your TokenMix API key.
Pricing
Input $0.588235/M tokens, output $1.764706/M tokens
Capabilities
Function calling, Streaming, Reasoning
Model specs
- Context: 128K tokens
- Max output: 32K tokens
Availability
3/3 available API endpoints are healthy right now.
Recent performance
TTFT 1239ms, latency 1730ms, throughput 32.6 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.