Qwen · Text
Qwen4-Max API pricing
qwen/qwen4-max
Flagship multimodal reasoning. Qwen4-Max by Qwen, routed through INFRO on a provider account you connect — alongside every other provider you run. Your provider bills you for it directly, on that account and at your own rate. INFRO adds routing, failover, request logs, cost attribution and policy around it, and takes no part of what you pay.
Pricing
Qwen rate
$2.25
per 1M tokens, billed to you by your provider
INFRO adds
$0
0% markup on model spend
Per-token rates
$1.50 / 1M input tokens·$4.50 / 1M output tokens·$0.075 / 1M cached input tokens
The headline figure above is these two blended at a 3:1 input:output ratio, so one number is comparable across modalities. Your own ratio will move it.
The vendor's list rate, read from Qwen's own page (opens in a new tab) on 2026-11-17. An organization on a negotiated rate enters its own in the console.
Calling Qwen4-Max
POST /v1/chat/completionscurl https://api.infro.io/v1/chat/completions \
-H "Authorization: Bearer $INFRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen4-max",
"messages": [{"role": "user", "content": "Hello"}]
}'What this modality supports
- Streaming
- Tool calling
- Structured outputs
- Prompt caching
Frontier and open-weight language models behind an OpenAI-compatible endpoint. Streaming, tool calling, structured outputs, and vision pass straight through — and prompt caching is priced at the provider's own cached rate.
Providers that serve Qwen4-Max
You request "qwen/qwen4-max" from INFRO; it sends each provider the id that provider expects. Connect your own account with any of them, and INFRO routes and fails over between the ones you connect.
| Provider | Model id sent |
|---|---|
| OpenRouter | qwen/qwen4-max |
Added to the INFRO model catalog on 2026-11-17. See every model or every provider you can connect.