TokenFlux is a transparent, semi-public AI model gateway that provides unified API access to multiple large language models with smart routing and usage-based billing.
词元流动 offers 1 LLM API models.
Speed benchmark average: 44 tok/s.
tokenflux.dev
Embed this health check image to show the provider's latest availability snapshot.
Launch speed test directly via URL parameters, automatically fill the form and start 5-round conversation speed test
baseUrl
apiKey
modelId
https://lmspeed.net/en?baseUrl=https%3A%2F%2Fapi.groq.com%2Fopenai%2Fv1&apiKey=gsk_xxx&modelId=llama-3.1-70b-versatile
Embed this supported models image to show the provider's model performance snapshot.
Embed this recent tests image to show the provider's latest benchmark snapshot.