Integrations · Copy-paste configs

Connect NovaToken to the tools you already use

NovaToken speaks the OpenAI API. So instead of learning a new SDK, you change two values in whatever you already have open — the base URL and the key. Below are the exact configs for 12 tools, including the ones that hide the setting in a submenu.

The three values every tool asks for
Base URL: https://api.novatoken.dev/v1
API key: your sk-... key from the dashboard
Model: one of the ids below — or auto to let the gateway pick
Model id (copy exactly)Use it forPrice / 1M in · out
deepseek-ai/DeepSeek-V4-FlashReasoning, docs, long context (1M). Cached input is $0.006.$0.30 · $1.20
Qwen/Qwen2.5-7B-InstructShort chat, classification, extraction — the cheap workhorse.$0.10 · $0.30
zai-org/GLM-5.3-FlashEveryday writing, bilingual content.$0.15 · $0.50
moonshotai/Kimi-K2.7-CodeAgentic coding, 262K context, multi-file refactors.$1.20 · $5.00
autoMixed traffic. Routed per request, billed at the model that answered.varies
SDKs Cursor Cline / Roo / Kilo Continue Open WebUI LibreChat LobeChat Cherry Studio SillyTavern Troubleshooting

SDKs and raw HTTP

Python — openai SDK

# pip install openai from openai import OpenAI client = OpenAI( api_key="sk-your-novatoken-key", base_url="https://api.novatoken.dev/v1", ) resp = client.chat.completions.create( model="deepseek-ai/DeepSeek-V4-Flash", messages=[{"role": "user", "content": "Hello"}], stream=True, ) for chunk in resp: print(chunk.choices[0].delta.content or "", end="")

Node / TypeScript — openai SDK

// npm i openai import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.NOVATOKEN_API_KEY, baseURL: "https://api.novatoken.dev/v1", }); const stream = await client.chat.completions.create({ model: "deepseek-ai/DeepSeek-V4-Flash", messages: [{ role: "user", content: "Hello" }], stream: true, }); for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");

curl — no dependencies

curl https://api.novatoken.dev/v1/chat/completions \ -H "Authorization: Bearer $NOVATOKEN_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"auto","messages":[{"role":"user","content":"Hi"}]}'

Cursor

  1. Settings → Models (Cmd/Ctrl + Shift + J).
  2. Paste the key into OpenAI API Key.
  3. Enable Override OpenAI Base URL → https://api.novatoken.dev/v1.
  4. Add model → deepseek-ai/DeepSeek-V4-Flash, then pick it in the chat model selector.

Cursor's Tab completion and its own agent may keep using your Cursor plan. A custom key applies to the model you select in chat.

Cline / Roo Code / Kilo Code

All three use the same panel — Settings → API Configuration:

FieldValue
API ProviderOpenAI Compatible
Base URLhttps://api.novatoken.dev/v1
API Keysk-...
Model IDdeepseek-ai/DeepSeek-V4-Flash

For large multi-file refactors, switch the model id to moonshotai/Kimi-K2.7-Code. Agents resend context every turn, so DeepSeek's cached-input price ($0.006/M) does a lot of work over a long session.

Continue

Edit ~/.continue/config.yaml:

models: - name: DeepSeek V4 Flash provider: openai model: deepseek-ai/DeepSeek-V4-Flash apiBase: https://api.novatoken.dev/v1 apiKey: sk-your-novatoken-key roles: - chat - edit - apply

Open WebUI

Docker one-liner:

docker run -d -p 3000:8080 \ -e OPENAI_API_BASE_URL=https://api.novatoken.dev/v1 \ -e OPENAI_API_KEY=sk-your-novatoken-key \ -v open-webui:/app/backend/data \ --name open-webui ghcr.io/open-webui/open-webui:main

Or in the admin UI: Settings → Connections → OpenAI API → set the URL and key, then add the model ids manually.

LibreChat

version: 1.2.8 endpoints: custom: - name: "NovaToken" apiKey: "sk-your-novatoken-key" baseURL: "https://api.novatoken.dev/v1" models: default: ["deepseek-ai/DeepSeek-V4-Flash", "Qwen/Qwen2.5-7B-Instruct", "auto"] fetch: false titleConvo: true modelDisplayLabel: "NovaToken"

LobeChat

Settings → Language Model → OpenAI: set the API Key to sk-... and the Proxy URL / Base URL to https://api.novatoken.dev/v1. Then add the model ids under “Custom models”.

Cherry Studio

Settings → Model Provider → OpenAI: API Host https://api.novatoken.dev/v1, API Key sk-..., then add models manually with the ids above.

SillyTavern

Connection settings → API: OpenAI-compatible → Base URL https://api.novatoken.dev/v1, key sk-..., model zai-org/GLM-5.3-Flash (good bilingual roleplay) or deepseek-ai/DeepSeek-V4-Flash.

Troubleshooting that actually resolves tickets

SymptomCause
401 invalid keyBase URL missing /v1, key pasted into an Anthropic field, or a trailing space in the key.
Empty model dropdownMost clients do not fetch the catalogue. Type the id by hand, character for character.
Requests hang, then time outA proxy or VPN in between is buffering SSE. Disable buffering, or test with curl first to isolate the network.
“Model not found”Hyphens vs underscores. It is DeepSeek-V4-Flash with hyphens and Qwen2.5-7B-Instruct with a dot.

FAQ

Can any OpenAI-compatible tool use NovaToken?

Yes, as long as it lets you set a custom base URL. If a tool only accepts a key with no base URL field, it is locked to its own backend.

Do streaming and tool calls work?

Yes — SSE streaming, function/tool calling and JSON mode, on every model including auto.

Is there a minimum spend?

$5, one time. No subscription, credits do not expire.

Can I use auto in a coding agent?

You can, but agents are exactly the workload where you want a known model — pin moonshotai/Kimi-K2.7-Code or deepseek-ai/DeepSeek-V4-Flash so behaviour stays consistent between turns.

One key, four models, card payment

DeepSeek · Qwen · GLM · Kimi. $5 to start, no subscription, billed per token at each model's own rate.

Buy $5 of credits