LiteLLM with GLM 5.3 Flash, DeepSeek V4.1 Flash and MiMo V2.6 Flash

Point LiteLLM at Pareto's OpenAI-compatible API to run GLM 5.3 Flash, DeepSeek V4.1 Flash and MiMo V2.6 Flash on Pareto GPUs. Pay per token from one prepaid balance.

Talk to us Get started

Setup

Get an API key in the dashboard, then add this to your router.

Add this model to your existing config. Keep your proxy access settings.

config.yamlYAML

model_list:
  - model_name: pareto-flash
    litellm_params:
      model: openai/z-ai/glm-5.3-flash
      api_base: https://api.paretoinference.com/v1
      api_key: os.environ/PARETO_API_KEY

Get started now

Full LiteLLM guide

Models

GLM 5.3 Flash$0.06 input, $0.20 output and $0.012 cached input per 1M tokens DeepSeek V4.1 FlashOff-peak: $0.105 input, $0.42 output and $0.0021 cached input per 1M tokens MiMo V2.6 Flash$0.126 input, $0.252 output and $0.00252 cached input per 1M tokens

Use LiteLLM with Pareto.