infer/shimme.rs

Documentation

Connect OpenCode or any OpenAI-compatible tool in a few minutes.

1

Get an API key

An admin adds you to the infer_users group of your shimme.rs ID. Then sign in and create a key on the overview page — it's shown once. Store it in a private file without leaving it in your shell history:

Terminal
mkdir -p ~/.config/opencode
(umask 077; read -rs KEY && printf '%s' "$KEY" > ~/.config/opencode/infer-key)
Base URL
https://infer.shimme.rs/v1
Model
qwen3.6-35b-a3b-uncensored
2

OpenCode

Add the provider to ~/.config/opencode/opencode.json, merging the providers block if the file exists. OpenCode reloads its config automatically.

~/.config/opencode/opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "providers": {
    "shimmers": {
      "name": "shimme.rs infer",
      "package": "@opencode/ai/providers/openai-compatible",
      "settings": {
        "baseURL": "https://infer.shimme.rs/v1",
        "apiKey": "{file:~/.config/opencode/infer-key}",
        "headerTimeout": 1860000,
        "cache": { "warming": false }
      },
      "models": {
        "qwen3.6-35b-a3b-uncensored": {
          "name": "Qwen3.6 35B-A3B Uncensored (shimme.rs GPU)",
          "capabilities": {
            "tools": true,
            "input": ["text"],
            "output": ["text"],
            "reasoning": { "supported": true }
          },
          "compatibility": { "reasoningField": "reasoning_content" },
          "limit": { "context": 65536, "output": 4096 },
          "variants": [
            { "id": "instant", "body": { "chat_template_kwargs": { "enable_thinking": false } } },
            { "id": "thinking", "body": { "chat_template_kwargs": { "enable_thinking": true } } }
          ]
        }
      }
    }
  }
}

Run /models and pick Qwen3.6 35B-A3B Uncensored (shimme.rs GPU), or try it from the terminal:

Terminal
opencode run --model shimmers/qwen3.6-35b-a3b-uncensored "hello"
Tips
  • Append #instant to the model for quick answers without thinking.
  • Keep cache.warming off — keep-alive pings would hold the GPU awake on your allowance.
  • OpenCode runs tools on your machine; only the conversation reaches the GPU.
  • Keep your usual model as default and switch per session to save minutes.
3

Other tools

Anything that accepts an OpenAI base URL works. Many tools read these variables:

Environment
export OPENAI_BASE_URL=https://infer.shimme.rs/v1
export OPENAI_API_KEY="$(cat ~/.config/opencode/infer-key)"

curl

Terminal
curl https://infer.shimme.rs/v1/chat/completions \
  -H "Authorization: Bearer $(cat ~/.config/opencode/infer-key)" \
  -H 'Content-Type: application/json' \
  -d '{"model":"qwen3.6-35b-a3b-uncensored","stream":true,"messages":[{"role":"user","content":"Hello"}]}'

Python

example.py
import os
from openai import OpenAI

key = open(os.path.expanduser("~/.config/opencode/infer-key")).read().strip()
client = OpenAI(base_url="https://infer.shimme.rs/v1", api_key=key, timeout=1900, max_retries=0)
stream = client.chat.completions.create(
    model="qwen3.6-35b-a3b-uncensored", stream=True,
    messages=[{"role": "user", "content": "Hello"}],
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="", flush=True)

API reference

GET /v1/modelsLists the available model.
POST /v1/chat/completionsText messages, streaming, JSON tool calls, response_format, stop.
Not supportedImages, embeddings, legacy completions, the Responses API. Sampling parameters are fixed to the model's recommended values.

Prefer streaming. Streaming requests get headers immediately plus keep-alive comments while the GPU wakes. Non-streaming requests wait silently, so give clients a 30-minute timeout.

Limits & privacy

Scale to zero

One shared GPU wakes on the first request and sleeps after 2 idle minutes. A cold start loads 18.7 GB of weights and takes a few minutes.

Sessions

A GPU session lasts up to 30 minutes; a request still running then is cut off and the next starts a fresh GPU.

Model limits

64k-token context, up to 4,096 output tokens (1,024 for thinking).

Allowance

Default 60 GPU-minutes per month, a shared platform cap and up to 4 queued requests per person. Resets on the 1st (UTC).

Privacy. Prompts and outputs pass through shimme.rs and are processed on a rented Runpod Secure Cloud GPU. Only usage counters are stored — never prompts or responses. The model is uncensored; you're responsible for how you use it.

Troubleshooting

authentication_errorKey missing, mistyped or revoked. Check the key file has no extra characters.
“API access needs renewal”Sign in here once; membership is re-confirmed every 30 days.
insufficient_quotaYour or the platform's monthly allowance is used up.
gpu_unavailableNo GPU within the price limit, a startup failure or cleanup in progress. Wait a minute and resend — clients deliberately don't retry automatically.
gpu_pausedAn admin paused the GPU.
rate_limit_errorQueue full; retry shortly.
First reply is slowNormal on a cold start; later replies are fast while the GPU is warm.