Use Chutes with SillyTavern

SillyTavern is a locally installed, open-source interface for chatting with text-generation LLMs and AI characters. Since version 1.15.0 it has a built-in Chutes connection, so all you need is a Chutes API key and a model. Requests go to the Chutes OpenAI-compatible API at https://llm.chutes.ai/v1.

Quick Reference

If your SillyTavern has no Chutes source, use Custom (OpenAI-compatible) with the base URL https://llm.chutes.ai/v1 instead. See Option B.

Before You Start

1. Create a Chutes account at chutes.ai/auth/signup.
2. Create an API key on the API Keys page with the Create Key button. Chutes keys start with cpk_. Copy the key straight away, because Chutes shows it only once.
3. Add credits or choose a plan. Chutes does not offer a free tier at the moment. Add credits on the Billing page, or pick a subscription on chutes.ai/pricing. See What It Costs.
4. Install SillyTavern 1.15.0 or later by following the official SillyTavern docs.

Option A: The Built-in Chutes Source (Recommended)

1. Open the API Connections panel, the plug icon in the top bar.
2. Set API to Chat Completion.
3. Set Chat Completion Source to Chutes.
4. Paste your key into Chutes API Key. SillyTavern hides the key after you connect.
5. Click Connect. SillyTavern loads the live model list from Chutes.
6. Choose a model in Chutes Model.
7. Click Test Message to check the connection. The test is a real request, so it is billed like any other.

With this source you never type a URL: SillyTavern sends requests to https://llm.chutes.ai/v1/chat/completions with your key as a Bearer token. The Model Sorting drawer can sort the Chutes model list by prompt price, completion price or context size.

SillyTavern 1.15.0 also added Chutes as an image generation source and a speech recognition source. This guide covers chat.

Option B: Custom (OpenAI-compatible)

Use this if your SillyTavern version has no Chutes source, or if you prefer the generic connection.

1. In API Connections, set API to Chat Completion and Chat Completion Source to Custom (OpenAI-compatible).
2. Set Custom Endpoint (Base URL) to https://llm.chutes.ai/v1. Do not add /chat/completions, because SillyTavern appends it for you.
3. Paste your key into Custom API Key.
4. Click Connect, then pick a model from Available Models or type its ID into Enter a Model ID.
5. Click Test Message to check the connection.

Choosing a Model

A Chutes model ID is the exact string sent as model, such as zai-org/GLM-5.1-TEE. Copy it exactly. To find IDs:

• Browse chutes.ai/models. On a model's page, the API tab shows the ID in the model field of its code examples.
• Open llm.chutes.ai/v1/models, the live model list in JSON. Each entry's id is a model ID, and the list needs no API key.

Three IDs from the live list on 2026-10-17: deepseek-ai/DeepSeek-V3.2-TEE, zai-org/GLM-5.1-TEE and moonshotai/Kimi-K2.6-TEE. They are examples, not recommendations. The catalog changes, so check the list before you pick.

The -TEE suffix means the model runs inside a Trusted Execution Environment, confidential-compute hardware that keeps prompts and outputs encrypted in memory. Every model in the live list on 2026-10-17 was a TEE model. More on chutes.ai/tee.

Chutes does not publish SillyTavern sampler presets. Good settings depend on the model; the API tab on each model page lists the request parameters it accepts.

What It Costs

SillyTavern traffic is billed like any other Chutes API use:

• Pay-as-you-go: per-token prices, charged separately for input and output and taken from your balance. There is no minimum commitment.
• Subscriptions: Plus at $10 per month and Pro at $20 per month each include a daily request quota. Requests beyond it are billed at pay-as-you-go rates, 6 percent off on Plus and 10 percent off on Pro.

Subscriptions are for casual use. The Terms of Service say: "Subscriptions are intended for casual, direct usage and not for use in large-scale automated inference, building production applications, or similar high-volume workloads. Acceptable use includes manual interactions and low-volume API usage." Current prices for every model are on chutes.ai/pricing.

Troubleshooting

To rule out SillyTavern itself, test your key from a terminal. A JSON reply with a choices array means the key, balance and model all work:

export CHUTES_API_KEY="cpk_..."

curl https://llm.chutes.ai/v1/chat/completions \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "zai-org/GLM-5.1-TEE",
       "messages": [{"role": "user", "content": "Hello"}],
       "max_tokens": 50}'

Privacy

The Chutes Privacy Policy says: "We do not log, store, or persist the content of your API requests or responses." It also explains how TEE models protect data while it is processed; see chutes.ai/tee for the hardware side.

Prefer a Ready-Made Roleplay App?

If you would rather not install and configure a frontend, fictio is an AI character chat and roleplay platform built by Chutes.

Related

• Use Chutes with JanitorAI
• The Chutes Starter Guide, from account to first API call
• SillyTavern on GitHub, and its documentation
• Questions about Chutes: the Chutes Discord