Model prices on QuickRouter
Usage is drawn from your balance at the listed price of each upstream model. The table below shows indicative list rates per 1M tokens for the models people ask about most; the console is the source of truth for live pricing.
Start here
Indicative list prices per 1M tokens
Prices are the upstream list rates the gateway bills against, so a call to any row below draws from your balance at that rate. Model names in the first group link to a page with worked cost examples.
| Vendor | Model | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| OpenAI | GPT-5 | 400K | $1.25 | $10.00 |
| OpenAI | GPT-5 mini | 400K | $0.25 | $2.00 |
| Anthropic | Claude Sonnet 4.5 | 200K | $3.00 | $15.00 |
| Anthropic | Claude Opus 4.1 | 200K | $15.00 | $75.00 |
| Anthropic | Claude Haiku 4.5 | 200K | $1.00 | $5.00 |
| Gemini 2.5 Pro | 1M | $1.25 | $10.00 | |
| Gemini 2.5 Flash | 1M | $0.30 | $2.50 | |
| DeepSeek | DeepSeek V3.2 | 128K | $0.28 | $0.42 |
| DeepSeek | DeepSeek R1 | 128K | $0.55 | $2.19 |
| xAI | Grok 4 | 256K | $3.00 | $15.00 |
| xAI | Grok 4 Fast | 2M | $0.20 | $0.50 |
| Qwen | Qwen3 Max | 256K | $1.20 | $6.00 |
| Zhipu | GLM-4.6 | 200K | $0.60 | $2.20 |
| Moonshot | Kimi K2 | 256K | $0.60 | $2.50 |
| MiniMax | MiniMax M2 | 200K | $0.30 | $1.20 |
| Mistral | Mistral Large 3 | 128K | $2.00 | $6.00 |
| Meta | Llama 4 Maverick | 1M | $0.27 | $0.85 |
| ByteDance | Seedance 2.0 | Video | per clip | per clip |
The table shows the models people ask about most, not the full catalogue. 8 vendors and 400+ models are reachable through the same endpoint; the console lists every id your key can call along with live pricing.
How model pricing works on the gateway
You pay two separate things: a gateway plan from $19 per month, and model usage drawn from your balance at the upstream list price of whichever model you call. There is no per-model markup and no rounding up.
- Input tokens are what you send: prompts, context, files and tool results.
- Output tokens are what the model generates, and they are usually the more expensive half - up to 8x on the GPT-5 tier.
- Agent loops re-read context on every step, so their cost tracks the input price rather than the output price.
One key covers every model in this guide
Create an account, pick a plan and copy an API key. Gateway plans start at $19 per month and model usage is billed at upstream list prices.