The enterprise gateway to
every frontier model.
Dancing AI gives your team a single OpenAI-compatible endpoint to GPT, Claude, Gemini and DeepSeek — with native streaming, token-level billing and documentation your finance team will actually accept.
Infrastructure your team can standardize on
Engineer-led team
Founded and run by infrastructure engineers. Support is answered by the people who operate the gateway — not a call-center script.
Official upstream channels
Every model is served through legitimate provider channels with enterprise-grade stability, so production traffic never rides on shaky accounts.
Invoice-ready billing
Bank-transfer top-ups with formal documentation for every payment — receipts your finance department can file without a follow-up email.
Pay per token
No subscriptions, no seats, no minimums. You are billed on the exact prompt and completion tokens reported by the upstream provider.
One gateway, every workload
Production applications
Power customer-facing features with GPT-4.1 or Claude Sonnet 4, and switch providers by changing one string when your needs change.
Large-scale data processing
Classification, extraction and enrichment pipelines over millions of rows, with per-token billing that keeps unit economics predictable.
Academic research
Give labs and research groups frontier-model access with transparent metering and formal documentation for every top-up.
Product prototyping
Try the same prompt across four providers in minutes. Compare quality, latency and cost before you commit to a model.
Model evaluation & distillation
Run evals against multiple frontier models through one client, then distill the results into smaller, cheaper deployments.
Developer tooling
Code assistants, reviewers and agents behind one audited endpoint, with live usage logs for every key you issue.
Live in three steps
Create an account
Sign up in seconds and open the console — no credit card required to explore.
Recharge your wallet
Request a top-up and our team sends you bank transfer details by email. Balance lands as soon as the transfer is confirmed.
Call the API
Create a key and start calling /v1/chat/completions. Costs are metered per token and visible in real time.
$ curl https://dancing.party/v1/chat/completions \
-H "Authorization: Bearer sk-dancing-…" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4.1",
"messages": [
{"role":"user","content":"Hello!"}
],
"stream": true
}'
# → 200 OK · SSE stream · billed per token| Model | Family | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
gpt-4.1 |
OpenAI | 1,047,576 | $2.00 | $8.00 |
gpt-4.1-mini |
OpenAI | 1,047,576 | $0.40 | $1.60 |
gpt-4o |
OpenAI | 128,000 | $2.50 | $10.00 |
gpt-4o-mini |
OpenAI | 128,000 | $0.15 | $0.60 |
o4-mini |
OpenAI | 200,000 | $1.10 | $4.40 |
claude-sonnet-4 |
Anthropic | 200,000 | $3.00 | $15.00 |
claude-3-5-haiku |
Anthropic | 200,000 | $0.80 | $4.00 |
gemini-2.5-pro |
1,048,576 | $1.25 | $10.00 |
From incorporation to frontier gateway
Dancing Technology Inc. incorporated
Founded in Denver, Colorado as an engineering company focused on AI infrastructure.
The Dancing AI gateway goes live
An OpenAI-compatible endpoint launches with native streaming, per-token billing and prepaid wallet top-ups.
Four providers, ten-plus models
GPT, Claude, Gemini and DeepSeek families served through official channels behind a single endpoint.
Enterprise tooling
Team workspaces, consolidated invoicing and spending controls for larger deployments.
Ship your next AI feature today
One endpoint. Every model. Usage-based pricing that scales down to zero.
Create free accountQuestions, answered
Which models are supported?
GPT-4.1, GPT-4o, o4-mini, Claude Sonnet 4, Claude 3.5 Haiku, Gemini 2.5 Pro / Flash and DeepSeek V3 / R1 are available at launch, with more added regularly. Check the Models page for the live catalog.
How does billing work?
Prepaid wallet, billed per token at each model's published rate. Prompt and completion tokens are metered separately using the usage reported by the upstream provider — nothing is estimated.
How do I recharge my wallet?
Submit a recharge request in the console and leave your contact email. Our support team replies with bank account details; once your transfer is confirmed your balance is credited. See the docs for details.
Is the API OpenAI-compatible?
Yes. The gateway implements /v1/chat/completions and /v1/models with the same request and response schema, including streaming via server-sent events.
Can I rotate or revoke keys?
Absolutely. Create unlimited keys from the console, and delete a key at any time to revoke it instantly.