---
title: "KoboldAI Lite custom API setup: OpenAI Compatible, no GPU"
canonical: https://relayswitch.io/guides/koboldai
generated: 2026-11-15T03:25:00.118Z
source: https://api.relayswitch.io/v1/catalog
base_url: https://api.relayswitch.io/v1
---

Checked 2026-11-03

# KoboldAI Lite custom API setup (OpenAI Compatible API)

Run KoboldAI Lite in the browser on RelaySwitch: one provider popup, the model id, chat-completions mode, and what each message costs. No GPU, no KoboldCpp.

KoboldAI Lite is the browser front-end that KoboldCpp ships; at [lite.koboldai.net](https://lite.koboldai.net) it runs on its own and connects to any API you give it. Choose **OpenAI Compatible API** as the provider, paste `https://api.relayswitch.io/v1` and your key, pick a model, and tick **Chat-Completions API**. Nothing to install, no model to download, every model in the catalog on one prepaid key.

## 01What you need

-   A browser. Lite keeps its stories in the browser's local storage; the **Save / Load** menu exports them.
-   A RelaySwitch key from the [console](https://app.relayswitch.io/console) (email code sign-in). Keys start with `sk-relay-`.
-   A balance. Top-ups start at $10, by card or crypto, with no subscription. Before the first top-up the console chat runs 12 free turns a day.

## 02The provider popup

Click **AI** in Lite's top bar. The **Select your AI provider** popup opens; set these:

text

1`Provider: OpenAI Compatible API`

2`OpenAI API URL: https://api.relayswitch.io/v1`

3`API Key (Required): sk-relay-...`

4`Model: Fetch, or Custom: glm-5.3-uncensored`

5`Chat-Completions API: ticked`

6`Use CORS Proxy: unticked`

1.  Provider: **OpenAI Compatible API** (under the custom endpoints, not the KoboldAI Remote API).
2.  **OpenAI API URL**: `https://api.relayswitch.io/v1`. Keep **Add Ver. Num** as it is; the URL already carries the `/v1`.
3.  **API Key (Required)**: your `sk-relay-` key.
4.  Click **Fetch**. Lite loads the model list your key can call from `/v1/models`; pick one. Or choose **Custom** and type the id exactly as the [Models page](https://relayswitch.io/models) prints it.
5.  Tick **Chat-Completions API**. It sends each turn as a chat request, which is what every model here answers; unticked, Lite uses the text-completions route and gets 404.
6.  Leave **Use CORS Proxy** unticked. The API accepts calls from any origin, so the key travels from your browser to the API and nowhere else.
7.  Click **Ok**. The model name appears in the top bar, and the first message is the test.

The **Favorites** row in the same popup saves the URL and key for next time.

## 03Settings that change the bill

-   **Usage Mode**: Story, Adventure, Chat or Instruct. Chat and Instruct map cleanly onto chat completions.
-   **Max Output**: the longest reply per turn. 300 is a paragraph; a model that reasons before it writes needs 1,000 or more, or the reply is cut inside the reasoning step and arrives empty.
-   **Context Size**: how much of the story Lite sends each turn. It is the number that sets the input side of the bill; keep it at or under the model's window.

## 04Which model to pick

Uncensored and roleplay builds first; the flagships for longer memory. Prices are per million tokens, and the turn columns price one 2K-in / 300-out turn: 2,000 tokens of story and memory in, 300 tokens out.

| Model | Model | Context | Input / M | Output / M | one 2K-in / 300-out turn | 100 turns |
| --- | --- | --- | --- | --- | --- | --- |
| [GLM-5.3 Flash Uncensored](https://relayswitch.io/models/glm-5.3-flash-uncensored) | `glm-5.3-flash-uncensored` | not stated | $0.1053 | $0.3685 | $0.00032 | $0.0321 |
| [GLM-5.3 Uncensored](https://relayswitch.io/models/glm-5.3-uncensored) | `glm-5.3-uncensored` | not stated | $0.282 | $0.846 | $0.00082 | $0.0818 |
| [Gemma 4 31B Fabled](https://relayswitch.io/models/gemma-4-31b-fabled) | `gemma-4-31b-fabled` | 262K tokens | $0.35 | $1.575 | $0.0012 | $0.1173 |
| [Qwen3.8 27B Novelist](https://relayswitch.io/models/qwen3.8-27b-novelist) | `qwen3.8-27b-novelist` | 262K tokens | $0.35 | $2.10 | $0.0013 | $0.133 |
| [Cydonia 24B v4.3](https://relayswitch.io/models/cydonia-24b-v4.3) | `cydonia-24b-v4.3` | 131K tokens | $0.484 | $0.60 | $0.0011 | $0.1148 |
| [Uncensored AI Roleplay](https://relayswitch.io/models/uncensored-ai-roleplay) | `uncensored-ai-roleplay` | 128K tokens | $0.60 | $2.34 | $0.0019 | $0.1902 |
| [DeepSeek V4.1 Flash Abliterated](https://relayswitch.io/models/deepseek-v4.1-flash-abliterated) | `deepseek-v4.1-flash-abliterated` | not stated | $0.8488 | $1.6975 | $0.0022 | $0.2207 |
| [DeepSeek V4 Pro Uncensored](https://relayswitch.io/models/deepseek-v4-pro-uncensored) | `deepseek-v4-pro-uncensored` | not stated | $0.97 | $1.94 | $0.0025 | $0.2522 |

USD, read from the RelaySwitch catalog when this page was built.

| Model | Model | Context | Input / M | Output / M | one 2K-in / 300-out turn | 100 turns |
| --- | --- | --- | --- | --- | --- | --- |
| [Claude Sonnet 4.6](https://relayswitch.io/models/claude-sonnet-4-6) | `claude-sonnet-4-6` | 1M tokens | $1.80 | $9.00 | $0.0063 | $0.63 |
| [Gemini 3.1 Pro Preview](https://relayswitch.io/models/gemini-3.1-pro-preview) | `gemini-3.1-pro-preview` | 1M tokens | $1.20 | $7.20 | $0.0046 | $0.456 |
| [DeepSeek V3.2](https://relayswitch.io/models/deepseek-v3.2) | `deepseek-v3.2` | not stated | $1.08 | $1.6801 | $0.0027 | $0.2664 |
| [Grok 4.6](https://relayswitch.io/models/grok-4.6) | `grok-4.6` | 500K tokens | $0.60 | $1.80 | $0.0017 | $0.174 |
| [GLM 5.3](https://relayswitch.io/models/glm-5.3) | `glm-5.3` | 1M tokens | $0.3178 | $0.9987 | $0.00094 | $0.0935 |

USD, read from the RelaySwitch catalog when this page was built.

The [uncensored models page](https://relayswitch.io/uncensored) lists every build the catalog tags.

## 05What a long story costs

Per message at three Context Size values, with a 300\-token reply:

| Context sent | Gemma 4 31B Fabled | GLM-5.3 Uncensored | Claude Sonnet 4.6 |
| --- | --- | --- | --- |
| 4,000 tokens | $0.0019 | $0.0014 | $0.0099 |
| 8,000 tokens | $0.0033 | $0.0025 | $0.0171 |
| 16,000 tokens | $0.0061 | $0.0048 | $0.0315 |

USD per message, read from the RelaySwitch catalog when this page was built.

Lite's **Context** panel holds Memory and World Info, which ride along on every turn too. The console's Usage page lists every request with its tokens and charge.

## 06Errors

-   `401`: the key is wrong or revoked. Paste it again in API Key (Required).
-   `402`: the balance is empty, or the key reached its budget. Top up or raise it in the console.
-   `404` `route_not_found`: Chat-Completions API is unticked, or the URL lost its `/v1`. `model_not_found`: a typed id that is not in the catalog; use Fetch.
-   A browser CORS error: Use CORS Proxy was ticked and the proxy is down. Untick it; this API needs no proxy.
-   `429`: the key hit its per-minute limit. Wait a few seconds. `503`: no host for that model right now; pick another.

## 07Sources

Labels from the provider popup at [lite.koboldai.net](https://lite.koboldai.net) and its source, [LostRuins/lite.koboldai.net](https://github.com/LostRuins/lite.koboldai.net), read 2026-11-03. KoboldCpp users: the same popup appears when KoboldCpp is launched with `--nomodel`, so a local install can use this key the same way.

## Questions

Can I use KoboldAI Lite without a GPU?

Yes. lite.koboldai.net runs in the browser and the model runs behind the API: OpenAI Compatible API as the provider, https://api.relayswitch.io/v1 as the URL, your key, a model from Fetch.

What is the KoboldAI Lite custom API URL?

https://api.relayswitch.io/v1, in the OpenAI API URL field of the OpenAI Compatible API provider, with Chat-Completions API ticked.

Do I need the CORS proxy in KoboldAI Lite?

Not for this API. It accepts calls from any origin, so leave Use CORS Proxy unticked; with it ticked, the key passes through the proxy instead of going straight to the API.

Why does Lite answer 404?

Chat-Completions API is unticked, so Lite called the text-completions route, which this API does not serve. Tick it and resend.

How much does a KoboldAI Lite message cost?

One 2K-in / 300-out turn on GLM-5.3 Flash Uncensored costs $0.00032 today, or $0.0321 for 100. Context Size sets the input side once the story fills it.

Related

-   [All guides](https://relayswitch.io/guides)
-   [SillyTavern](https://relayswitch.io/guides/sillytavern)
-   [Agnai](https://relayswitch.io/guides/agnai)
-   [JanitorAI](https://relayswitch.io/guides/janitorai)
-   [RisuAI](https://relayswitch.io/guides/risu)
-   [Roleplay chat](https://relayswitch.io/roleplay)
-   [Uncensored models](https://relayswitch.io/uncensored)
-   [Models and prices](https://relayswitch.io/models)
-   [How pricing works](https://relayswitch.io/pricing)
-   [Pay by card or crypto](https://relayswitch.io/pay-with-crypto)
-   [Docs](https://relayswitch.io/docs)

## Every model in KoboldAI Lite, no GPU

Prepaid from $10 by card or crypto. No KYC, no subscription.

[Models](https://relayswitch.io/models)[Get a key](https://app.relayswitch.io/console)