Leading models.
One API.

Gabnode gives your applications access to models from OpenAI, Anthropic, Google, DeepSeek and others through a single OpenAI-compatible API. One account, one prepaid balance, and per-token rates published for every model.

Get started View models

19 models from 8 providers
OpenAI-compatible API
Prepaid, billed per token

Same request, another model

AnthropicOpenAIGoogleDeepSeek

POSTapi.gabnode.com/v1/chat/completions

{
  "model": "claude-sonnet-5-5",
  "messages": [
    { "role": "system",
      "content": <policy manual> },
    { "role": "user",
      "content": "Can I switch plans?" }
  ]
}

Response

Yes. Plan changes take effect immediately, and the remaining days of the current cycle are credited to the new plan (section 4.2)…

Usage

Model: claude-sonnet-5-5

Input2,449 tokens × $2.00 / 1M: $0.0049
Cached input51,092 tokens × $0.20 / 1M: $0.0102
Output1,180 tokens × $10.00 / 1M: $0.0118

Charged: $0.0269
Balance: $250.00 → $249.97

Illustrative request priced at current catalog rates. Token counts vary slightly between model families.

Models available through Gabnode from

OpenAI
Anthropic
Google
DeepSeek
Z.ai
Moonshot AI
MiniMax
Qwen

Why Gabnode

Less to manage between your product and the models it uses.

Working with several model providers usually means several accounts, keys, invoices and request formats. Gabnode puts them behind one integration.

Working with each provider directly compared with using Gabnode
Aspect	With each provider directly	Through Gabnode
Accounts	One per provider	One Gabnode account
API keys	Separate keys in each console	Gabnode keys you create, rotate and revoke in one place
Billing	A payment method and invoice per provider	One prepaid balance, shared by every model
Integration	Different SDKs and request formats	One OpenAI-compatible API
Changing models	Often new integration work	Change the model parameter
Usage	Spread across provider consoles	One usage history, itemised by request and model

Models

Models available through Gabnode.

Frontier and open-weight models from leading labs, behind one endpoint. Choose the right model for each request, and change your mind without changing your integration.

OpenAI
- GPT-6 Astragpt-6-astraMost capable1M context
- GPT-6.1 Solgpt-6.1-solBalanced1M context
- GPT-6 Lunagpt-6-lunaFast, low cost400K context
Anthropic
- Claude Fable 5.1claude-fable-5-1Most capable1M context
- Claude Opus 5.5claude-opus-5-5Most capable1M context
- Claude Sonnet 5.5claude-sonnet-5-5Balanced1M context
- Claude Haiku 5.5claude-haiku-5-5Fast, low cost1M context
Google
- Gemini 3.1 Progemini-3.1-proMost capable1M context
- Gemini 3.8 Flashgemini-3.8-flashBalanced1M context
- Gemini 3.5 Flash-Litegemini-3.5-flash-liteFast, low cost1M context
DeepSeek
- DeepSeek V4 Prodeepseek-v4-proMost capable256K context
- DeepSeek V4.1 Flashdeepseek-v4.1-flashFast, low cost256K context
Z.ai
- GLM-5.2glm-5.2Most capable200K context
- GLM-5.3 Flashglm-5.3-flashFast, low cost200K context
Moonshot AI
- Kimi K3kimi-k3Most capable256K context
- Kimi K2.6kimi-k2.6Balanced256K context
MiniMax
- MiniMax M3minimax-m3Balanced1M context
Qwen
- Qwen3.8 Maxqwen3.8-maxMost capable262K context
- Qwen3.8 Flashqwen3.8-flashFast, low cost1M context

Compare all 19 models

Availability can change. Your application can always fetch the current list from GET /v1/models.

How it works

From sign-up to first request.

Create an account
Sign up in the Gabnode dashboard. One account covers every model we serve.
Add balance
Top up a prepaid balance. It is shared across all models, so there is nothing to allocate.
Create an API key
Generate a key for each application or environment. Rotate or revoke keys at any time.
Send requests
Call the API with the model you want. Each request is charged at that model’s published rate.

Pricing

Per-token rates, published for every model.

Each request draws down your prepaid balance at the model’s published rate. You pay for the tokens you use, from a balance you control.

Input tokens: The text and images you send: system instructions, messages, tool definitions.
Cached input: Repeated prompt prefixes, such as long instructions or documents, served from cache at a reduced rate on models that support it.
Output tokens: Everything the model generates, including reasoning tokens on models that produce them.

Selected model rates in US dollars per million tokens
Model	Input	Cached input	Output
Claude Sonnet 5.5claude-sonnet-5-5	$2.00	$0.20	$10.00
GPT-6.1 Solgpt-6.1-sol	$2.00	$0.20	$10.00
Gemini 3.8 Flashgemini-3.8-flash	$0.75	$0.075	$3.75
DeepSeek V4 Prodeepseek-v4-pro	$1.74	$0.145	$3.48
Kimi K2.6kimi-k2.6	$0.95	$0.16	$4.00
Qwen3.8 Flashqwen3.8-flash	$0.15	$0.03	$0.47

USD per 1 million tokens. A dash means cached input is not offered for that model.

Full rate card and cost estimator

Developers

Point an OpenAI-compatible client at Gabnode.

Use the official OpenAI SDKs or any client that lets you set a base URL. Set your Gabnode key, change the base URL, choose a model.

Base URL: https://api.gabnode.com/v1
Authentication: Your API key as a bearer token in the Authorization header.
Endpoints: /v1/chat/completions with streaming, and /v1/models for the current model list.
Model features: Tool calling, structured output and image input work wherever the selected model supports them.

curl https://api.gabnode.com/v1/chat/completions \
  -H "Authorization: Bearer $GABNODE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5-5",
    "messages": [
      {"role": "user", "content": "Summarise this changelog in three bullet points."}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.gabnode.com/v1",
    api_key=os.environ["GABNODE_API_KEY"],
)

response = client.chat.completions.create(
    model="gpt-6.1-sol",
    messages=[{"role": "user", "content": "Summarise this changelog in three bullet points."}],
)

print(response.choices[0].message.content)
print(response.usage)  # tokens billed for this request

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.gabnode.com/v1",
  apiKey: process.env.GABNODE_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "gemini-3.8-flash",
  messages: [{ role: "user", content: "Draft release notes for version 2.4." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

curl https://api.gabnode.com/v1/models \
  -H "Authorization: Bearer $GABNODE_API_KEY"

Keep your key in an environment variable or secret store. Never ship it in client-side code.

Works with tools you already use

These SDKs, frameworks and applications accept a custom OpenAI-compatible endpoint. Which features are available depends on the client and the model; the documentation covers setup.

SDKs and frameworks

OpenAI Python SDK
OpenAI Node.js SDK
Vercel AI SDK
LangChain
LlamaIndex
LiteLLM

Editors and coding agents

Continue
Cline
Roo Code
Zed
Aider

Chat interfaces

Open WebUI
LibreChat
Jan
Chatbox

Dashboard

Your balance, keys, usage and support in one account.

Balance: See your balance at any time, top up when you need to and review past purchases.
API keys: Create keys per application or environment. Rotate or revoke them yourself, instantly.
Usage: Requests, tokens and spend, broken down by model, so costs are never a surprise.
Support: Open a ticket, follow its history and close it once it’s resolved.

Open the dashboard

Northwind Labs

Balance

$1,284.60

Prepaid · shared across all models

Add balance

Usage by model this month

claude-sonnet-5-5182.4M$412.18
gpt-6-luna611.0M$96.73
deepseek-v4.1-flash74.9M$31.40

API keys

production••••a41cRotateRevoke
staging••••9e07RotateRevoke
eval-runner••••13bdRotateRevoke

+ Create key

Support

Higher rate limit for productionOpen
Invoice details for Q3Closed

Illustration of an account in the Gabnode dashboard: prepaid balance, usage by model, API keys and support requests.

Documentation

Everything you need to integrate, in one place.

Quick start
Authentication
Chat completions
Streaming
Tool calling
Structured output
Listing models
Errors and rate limits
Usage and billing

Read the documentationdocs.gabnode.com

Questions

Common questions.

What is Gabnode?

Gabnode is an API platform for AI models. One account, one API and one prepaid balance give you access to models from several providers. You integrate once and choose the model on each request.

Is Gabnode affiliated with OpenAI, Anthropic, Google or the other model providers?

No. Gabnode is an independent company and is not affiliated with, or endorsed by, the companies whose models are available through its API. Model names are trademarks of their respective owners.

How does billing work?

You add funds to a prepaid balance in the dashboard. Each request is charged for its input, cached input and output tokens at the model’s published rate, and the amount is deducted from your balance. Your usage history shows what each request cost.

See Pricing for every rate.

What happens when my balance runs out?

Requests are declined with a clear error instead of running up a bill. Add balance in the dashboard and you can continue straight away.

Is the API compatible with OpenAI’s?

Gabnode provides an OpenAI-compatible Chat Completions API, so the official OpenAI SDKs and many other clients work by changing the base URL and API key. Features such as tool calling or image input depend on the model you choose. Where behaviour differs, the documentation says so.

How are tokens counted?

Each model counts tokens with its own tokenizer, so the same text can produce slightly different counts on different models. Every response includes a usage object with the exact counts billed for that request.

Can I use separate keys for different projects?

Yes. Create a key for each application or environment, and rotate or revoke any of them from the dashboard. All keys draw from your account’s balance.

How do I get help?

Open a support ticket from the dashboard to keep the whole conversation in one place, or email support@gabnode.com.

One account. One balance. One API.

Create an account, add balance and make your first request with the client you already use.

Get started Read the documentation

Leading models.One API.

Models available through Gabnode from

OpenAI

Anthropic

Google

DeepSeek

Z.ai

Moonshot AI

MiniMax

Qwen

Create an account