Low-cost open-weight model API | Simple Inference Service

Simple
Inference for
Open Models

Run open-weight language models through an OpenAI-style API. Choose a model and pay for the tokens you use.

Tool calls are now supported in Chat Completions, including streaming. Tool calling API docs.

Translating dialogue, app strings, or game text? Explore translations

curl https://api.simpleinferenceservice.com/v1/chat/completions \
  -H "Authorization: Bearer " \
  -H "Content-Type: application/json" \
  -d '{
  "model": "HauhauCS/Qwen3.8-27B-Uncensored-Aggressive",
  "stream": false,
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant. Keep replies clear and concise."
    },
    {
      "role": "user",
      "content": "Explain a token in one sentence."
    }
  ]
}'

API reference

Price Schedule

US dollars per million tokens
Model	Input	Output
`HauhauCS/Qwen3.8-27B-Uncensored-Aggressive`	$0.85	$2.25

Input and output tokens are billed separately using the token counts returned by the model. A model may take a few seconds to load. Queued requests can take longer.

API Documentation

See the API reference for chat, tool calls, responses, and streaming, or use the OpenAPI specification.

Using SIS for translation? See translation examples.

Point your agent at this page

This site is agent friendly. Point your agent at this page to sign up or sign in using an email inbox it can read.

Or sign up and get an API key yourself.

Support