Router de IA

One endpoint, many models

Router de IA

A single OpenAI-compatible endpoint that reaches many AI models with one API key.

No account with each provider, no separate bill for each one, no code to rewrite when you change model. You add credit, you create a key, and you use it from whatever you already build with.

See it in under a minute

How it works

Four steps, and no subscription anywhere in them.

  1. Add credit

    Choose an amount and pay the invoice. The credit lands in your account and stays there until you use it.

  2. Create an API key

    From your panel, in seconds. You choose which models each key may reach, and you can have as many keys as you need.

  3. Point your client at the endpoint

    Any OpenAI-compatible library, tool or agent: set the base URL and your key, name a model, and it answers.

  4. Pay only for what you use

    Consumption is discounted from your credit by tokens used. Nothing renews on its own: you top up when you want to.

Where it runs

Three tiers, one endpoint and one key. You choose per request, by naming the model.

Shared local infrastructure Recommended by Dongee 18

Shared local infrastructure, located entirely in Canada and outside United States law.

Dongee sovereign infrastructure 1

Dongee's own hardware, not shared with anyone. It does not pass through any datacenter in the United States or in China, and it is not subject to their laws.

Proveedores externos 11

Third-party providers, reached through the same endpoint and the same key.

Models and prices

Show the list Hide the list

You pay for what you use and nothing else. No subscription, no minimum, no charge for keys or requests that fail.

General purpose USD per million tokens

Infraestructura compartida local
local/gpt-oss-120b
in $0.126
out $0.658
Infraestructura compartida local
local/gpt-oss-20b
in $0.07
out $0.252
Infraestructura compartida local
local/llama-3.3-70b
in $1.036
out $1.036
Infraestructura compartida local
local/mistral-7b
in $0.154
out $0.154
Infraestructura compartida local
local/mistral-nemo
in $0.196
out $0.196
Infraestructura compartida local
local/mistral-small-3.2-24b
in $0.14
out $0.434
Infraestructura compartida local
local/qwen3.5-397b
in $0.994
out $5.95
Infraestructura compartida local
local/qwen3.5-9b
in $0.168
out $0.252
Infraestructura soberana de Dongee
sovereign/qwen3-30b (coming soon)
in $0.67
out $0.67
Proveedores externos
nvidia/gpt-oss-20b
in —
out —
Proveedores externos
nvidia/ising-calibration-1.5-31b
in —
out —
Proveedores externos
nvidia/laguna-xs-2.1
in —
out —
Proveedores externos
nvidia/muse-glimmer-30b
in —
out —
Proveedores externos
nvidia/nemotron-3-embed-1b
in —
out —
Proveedores externos
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
in —
out —
Proveedores externos
nvidia/nemotron-3-super-120b-a12b
in —
out —
Proveedores externos
nvidia/nemotron-parse-2.0
in —
out —

Programming USD per million tokens

Infraestructura compartida local
local/qwen3-coder-30b
in $0.098
out $0.364

Image understanding USD per million tokens

Infraestructura compartida local
local/qwen2.5-vl-72b
in $1.414
out $1.414
Infraestructura compartida local
local/qwen3.6-27b
in $0.658
out $4.466
Infraestructura compartida local
local/qwen3.8-27b
in $0.658
out $4.466
Proveedores externos
nvidia/llama-nemotron-embed-vl-1b-v2
in —
out —

Image generation per image

Infraestructura compartida local
local/sdxl-base-v10
per image —
Proveedores externos
nvidia/diffusiongemma-26b-a4b-it
per image —

Embeddings and search USD per million tokens

Infraestructura compartida local
local/bge-m3
in $0.014
Infraestructura compartida local
local/bge-multilingual-gemma2
in $0.014
Infraestructura compartida local
local/qwen3-embedding-8b
in $0.168

Moderation USD per million tokens

Infraestructura compartida local
local/qwen3guard-gen-0.6b
in —
out —
Infraestructura compartida local
local/qwen3guard-gen-8b
in —
out —
Proveedores externos
nvidia/llama-3.1-nemotron-safety-guard-8b-v3
in —
out —

Embeddings are billed on input only, because they return vectors and not tokens. Image models are billed per image. Speech to text is billed per minute of audio. Everything else is billed on the tokens that go in and the tokens that come out.

Start with whatever amount you want

Sign in to your account to get it. If you do not have one yet, creating it takes a minute.