CreateOS AI Gateway Pricing
One API for every model, routed to the cheapest available source, plus a flat 2.5% platform fee. Compare live prices across nine providers and model your spend.
Cost calculator
1.00M tokens
0.20M tokens
Input cost
$5.00
Output cost
$5.00
Base total
$10.00
Before platform fee
Total with 2.5% fee
$10.25
Final billed amount
Prices are the base upstream cost per 1M tokens. A flat 2.5% platform fee applies. The Gateway routes each request to the cheapest available source.
| Model | Provider | Context | Input $/1M | Output $/1M | Blended $/1M |
|---|---|---|---|---|---|
| Claude Opus 4.7 | Anthropic | 1M | $5.00 | $25.00 | $10.00 |
| Claude Opus 4.6 | Anthropic | 200K (1M β) | $5.00 | $25.00 | $10.00 |
| Claude Sonnet 4.6 | Anthropic | 200K (1M β) | $3.00 | $15.00 | $6.00 |
| Claude Opus 4.5 | Anthropic | 200K | $5.00 | $25.00 | $10.00 |
| Claude Sonnet 4.5 | Anthropic | 200K | $3.00 | $15.00 | $6.00 |
| Claude Haiku 4.5 | Anthropic | 200K | $1.00 | $5.00 | $2.00 |
| GPT-5.4 | OpenAI | 1.05M | $2.50 | $5.00 | $3.13 |
| GPT-5.4 Pro | OpenAI | 1.05M | $30.00 | $180.00 | $67.50 |
| GPT-5.4 Mini | OpenAI | 400K | $0.75 | $4.50 | $1.69 |
| GPT-5.4 Nano | OpenAI | 400K | $0.20 | $1.25 | $0.46 |
| GPT-5-mini | OpenAI | 400K | $0.25 | $2.00 | $0.69 |
| o4-mini | OpenAI | 200K | $1.10 | $4.40 | $1.93 |
| GPT-4.1 | OpenAI | 1M | $2.00 | $8.00 | $3.50 |
| GLM-5 | Zhipu AI | 200K | $0.30 | $2.43 | $0.83 |
| GLM-5.1 | Zhipu AI | 203K | $0.95 | $3.15 | $1.50 |
| GLM-5 Turbo | Zhipu AI | 200K | $0.96 | $3.20 | $1.52 |
| GLM-4.7 | Zhipu AI | 200K | $0.40 | $1.75 | $0.74 |
| GLM-4.7-Flash | Zhipu AI | 200K | FREE | FREE | FREE |
| Kimi K2.5 | Moonshot AI | 256K | $0.45 | $2.32 | $0.92 |
| Kimi K2 | Moonshot AI | 131K | $0.55 | $2.20 | $0.96 |
| Kimi K2 Turbo | Moonshot AI | 131K | $0.50 | $2.11 | $0.90 |
| Gemini 3.1 Pro Preview | 1M | $2.00 | $12.00 | $4.50 | |
| Gemini 2.5 Pro | 1M | $1.25 | $10.00 | $3.44 | |
| Gemini 3 Flash Preview | 1M | $0.50 | $3.00 | $1.13 | |
| Gemini 2.5 Flash | 1M | $0.30 | $0.30 | $0.30 | |
| Gemini 2.5 Flash-Lite | 1M | $0.10 | $0.40 | $0.18 | |
| Gemini 3.1 Flash Lite | 1M | $0.25 | $1.50 | $0.56 | |
| Gemini 3 Pro | 1M | $2.00 | $12.00 | $4.50 | |
| MiniMax M2.5 Standard | Minimax | 1M | $0.28 | $1.00 | $0.46 |
| MiniMax M2.7 | Minimax | 205K | $0.30 | $1.20 | $0.52 |
| MiniMax-01 | Minimax | 4M | $0.20 | $1.10 | $0.43 |
| MiniMax M2.1 | Minimax | 196K | $0.27 | $0.95 | $0.44 |
| Qwen3.5 Plus | Alibaba | 1M | $0.26 | $1.56 | $0.58 |
| Qwen 3.6 Plus | Alibaba | 1M | $0.33 | $1.95 | $0.73 |
| Qwen3.5 Flash | Alibaba | 1M | $0.10 | $0.40 | $0.18 |
| Qwen3 Max | Alibaba | 262K | $1.20 | $6.00 | $2.40 |
| Qwen3 Coder | Alibaba | 262K | $0.22 | $0.90 | $0.39 |
| Mistral Small 4 | Mistral | 262K | $0.10 | $0.30 | $0.15 |
| DeepSeek (Latest) | DeepSeek | 128K | $0.28 | $0.42 | $0.32 |
Prices are the base upstream cost per 1M tokens. A flat 2.5% platform fee applies. The Gateway routes each request to the cheapest available source.
Zero Data Retention Available
Zero Data Retention (ZDR) is available for supported models: the Gateway does not store your data and does not train on it. Ask for a ZDR-compliant model when you request access.
Common Questions
What is the CreateOS AI Gateway?
The CreateOS AI Gateway is a unified API gateway that routes every model request to the cheapest available upstream source. You reach dozens of models from nine providers through one endpoint, with one API key and one bill.
How does pricing work?
The prices shown are the base upstream cost per 1 million tokens. The Gateway adds a flat 2.5% platform fee and routes each request to the cheapest available source, so you always pay the lowest rate. No hidden fees, no minimums, no monthly commitment.
What is blended pricing?
Blended pricing is a weighted average that reflects typical usage: input cost times three, plus output cost, divided by four. Most calls send more input than they receive as output, so this gives a realistic per-million-token estimate.
Can I switch models without changing code?
Yes. Every model is available through the same endpoint, so switching is as simple as changing the model name in your request. No new SDK and no code changes.
What happens if a provider goes down?
The Gateway monitors upstream health in real time and reroutes to the next cheapest available source on an outage, so you get built-in redundancy at no extra cost.
Are there minimums or hidden fees?
No. You pay the upstream token cost plus the flat 2.5% platform fee. No minimums, no monthly charges, and no volume requirements.
One API for every model, at the cheapest price.
Book a demo, or start building on the Gateway.