How do I use Qwen 3.7 Plus in OpenCode or Cline without per-token billing?
Qwen 3.7 Plus (qwen/qwen3.7-plus) is included in every Standard Compute plan from $19 a month; OpenCode, Cline and Hermes reach it with one OpenAI-compatible key and no Alibaba Cloud account, and the plan's budget answers HTTP 402 once it is used up.
| Model | The lower-cost hosted model in Alibaba's Qwen 3.7 line (snapshot of May 26, 2026), with a 1M-token context and text and image input. |
|---|---|
| Model ID | qwen/qwen3.7-plusShort form qwen3.7-plus also works |
| Base URL | https://api.stdcmpt.com/v1 |
| Input | Text and images |
| Reasoning | On or off, per request or on the Models page |
Copy a working config
Paste the config for your agent. In OpenCode, many setups keep a stronger main model and give Plus the long, simple reads.
{
"$schema": "https://opencode.ai/config.json",
"model": "standardcompute/qwen/qwen3.7-plus",
"provider": {
"standardcompute": {
"npm": "@ai-sdk/openai-compatible",
"name": "Standard Compute",
"options": {
"baseURL": "https://api.stdcmpt.com/v1",
"apiKey": "{env:STANDARDCOMPUTE_API_KEY}"
},
"models": {
"qwen/qwen3.7-plus": { "name": "Qwen 3.7 Plus" },
"standardcompute": { "name": "Smart routing" }
}
}
}
}
Replace YOUR_API_KEY with a key from the dashboard. This config reads your key from STANDARDCOMPUTE_API_KEY; export it with a key from the dashboard. Full setup: OpenCode, Cline, Aider and other tools, Hermes.
What it costs
| Per 1M tokens | Prompt up to 256K | 256K to 1M |
|---|---|---|
| Input | $0.40 | $1.20 |
| Output | $1.60 | $4.80 |
Alibaba Cloud Model Studio list price, international (Singapore) deployment, the same with thinking on or off. Alibaba currently shows a limited-time 20% discount on both tiers. Source: Alibaba Cloud Model Studio pricing, checked October 13, 2026.
At $0.40 per million input tokens, a Plus-only workload rarely needs a plan. Note the tier line at 256K: past it, input triples to $1.20.
What works differently here
- Artificial Analysis rates Plus 25 and measures about 56 output tokens per second, which it places at the lower end of Plus's price tier. For comparison, it measures DeepSeek V4.1 Flash at about 190.
- The newer Qwen 3.8 models are on every plan too: Qwen 3.8 Max for hard steps, 27B and Flash for volume.
- Reasoning only switches on or off. In our tests, turning it off cut the median response time from about a minute to about a second.
Other ways to run Qwen 3.7 Plus
| Alibaba Model Studio$0.40 / $1.60 per 1M | First-party, with a tiered rate past 256K and a current 20% discount. |
|---|---|
| OpenRouterPay per token | Served by Alibaba, with one account for other vendors. |
| Standard ComputeMonthly plan | Plus with Qwen 3.7 Flash and Max and the Qwen 3.8 line, no Alibaba region to pick. |
FAQ
Qwen 3.7 Plus or Qwen 3.8 Flash?
Qwen 3.8 Flash is the newer model and Alibaba lists it at $0.15 / $0.47 per million tokens, well under Plus. Both read images and both are on every plan.
Qwen 3.7 Plus or Gemini 3.1 Pro?
Gemini 3.1 Pro scores higher on Artificial Analysis's Intelligence Index (30 against 25) and costs several times more per token. Use Plus for cheap long-context reading and Gemini 3.1 Pro where quality matters.
Do I need an Alibaba Cloud account?
No. You call Plus with a Standard Compute key; Alibaba's account, region choice and top-ups stay out of it.
Sources: Alibaba Cloud Model Studio pricing; Artificial Analysis: Qwen3.7 Plus
Plans from $19/mo
One key for Qwen 3.7 Plus and the rest of the catalog, with a monthly compute budget you can watch in the dashboard and no overage charges.