Skip to content

Models

Model IDProviderInput PriceOutput PriceContextBest For
deepseek-chatDeepSeek$0.14 / 1M$0.28 / 1M128KGeneral purpose, coding, analysis
deepseek-reasonerDeepSeek$0.55 / 1M$2.19 / 1M128KReasoning, math, logic (R1)
qwen-maxAlibaba$0.50 / 1M$1.50 / 1M32KMultilingual, translation
qwen-plusAlibaba$0.20 / 1M$0.60 / 1M128KBalanced price-performance
glm-4Zhipu$0.10 / 1M$0.10 / 1M128KChinese-optimized

Our most popular model. Excellent for:

  • General conversation and chat
  • Code generation and debugging
  • Content writing and summarization
  • Data analysis

Reasoning specialist. Best for:

  • Complex math problems
  • Logic puzzles
  • Multi-step reasoning
  • Problem-solving

Alibaba’s flagship model. Best for:

  • Multilingual tasks
  • English-Chinese translation
  • Document understanding
  • Long-form content

Zhipu’s model optimized for:

  • Chinese language scenarios
  • Enterprise applications
  • Cost-sensitive workloads

For OpenAI SDK compatibility, you can use these aliases:

AliasMaps To
gpt-4deepseek-chat
gpt-3.5-turboqwen-plus