qwen3.7-plusQwen3.7 Plus is the best-value model in the Qwen3.7 family — strong reasoning and agent ability at a fraction of Max’s price, with a 1M-token context window and hybrid thinking (reasoning_content). Tool calling, JSON output and streaming, served OpenAI-compatible via /v1/chat/completions.
View complete API reference with all parameters and examples.
View complete API reference with streaming, thinking, and more.
Billing: Cost = (input_tokens * input_price + output_tokens * output_price) / 1,000,000
Qwen3.7 reasoning at ~1/5 the price of Max
Million-token context window
Returns reasoning_content. For simple or bulk tasks pass enable_thinking:false to skip thinking and cut output cost sharply.
Function calling + JSON output, OpenAI-compatible
Qwen3.7 Plus is a Large Language Model API provided by Alibaba. Qwen3.7 Plus is the best-value model in the Qwen3.7 family — strong reasoning and agent ability at a fraction of Max’s price, with a 1M-token context window and hybrid thinking (reasoning_content). Tool calling, JSON output and streaming, served OpenAI-compatible via /v1/chat/completions. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: Input: $0.36, Output: $1.44 per 1M tokens.
Build intelligent conversational systems to automatically answer user queries and improve service efficiency.
Automatically write articles, emails, ad copy, and other text content to boost productivity.
Assist with code writing, debugging, and code review to accelerate software development.
Understand and analyze unstructured data, extract key insights, and generate summary reports.
Qwen3.7 Plus is available through APIMODELS at: Input: $0.36, Output: $1.44 per 1M tokens. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
APIMODELS offers the same Qwen3.7 Plus model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
Plus is the value tier of the same Qwen3.7 generation, not a warmed-over older model: same 1M-token context, same hybrid thinking, same tool calling and streaming. The gap shows up on the hardest multi-step reasoning and long-horizon agent runs, where Max holds together better. The price gap is wide — Plus $0.36 / $1.44 against Max $2.25 / $6.75, a 6.3x difference on input. Start on Plus and escalate the specific tasks it gets wrong to Max; it is a one-field change on the same endpoint.
$0.36 per 1M input and $1.44 per 1M output, cached input $0.072 — all 10% below Alibaba official USD pricing. One tier to know about: a request whose input exceeds 256K tokens (262,144) bills the whole request at 3x — $1.08 input, $4.32 output, $0.216 cached. That is the upstream step, passed through as-is with no markup of ours. Anything under 256K is unaffected.
POST https://api.apimodels.app/v1/chat/completions with Authorization: Bearer YOUR_API_KEY and body {"model":"qwen3.7-plus","messages":[{"role":"user","content":"..."}]}. Plain OpenAI shape — point openai-python or openai-node at base_url=https://api.apimodels.app/v1 and it works unchanged. Add stream:true for streaming; we measured it delivering genuinely incremental chunks rather than one buffered flush at the end.
Because thinking is ON by default, and reasoning tokens sit inside completion_tokens and bill at the output rate. Measured: a "write 60 words" prompt returned 3,783 completion tokens, 3,715 of them thinking, with 39 seconds to first output. The same prompt with enable_thinking:false returned 72 tokens in 1.2 seconds. For bulk work, format conversion and summarisation, pass enable_thinking:false; if you want some reasoning with a predictable ceiling, use thinking_budget.
Qwen's training leans heavily Chinese, and Chinese comprehension, long Chinese documents and Chinese writing are where it is strongest — which is why many teams in China pick it over Western models at the same price point. The 1M-token context means a whole manual or codebase fits in a single request. Reachable directly from mainland China with no Alibaba Cloud account.
On APIMODELS, Qwen3.7 Plus runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Reasoning / Thinking, Best Value, 1M Context, Tool Calling, Streaming, and you can weigh it on price and capability against other Large Language Model models, then switch by changing a single model-name string — no new account or integration. Browse every Large Language Model option with live pricing at apimodels.app/models.
Qwen3.7 Plus supports: Reasoning / Thinking, Best Value, 1M Context, Tool Calling, Streaming. See the APIMODELS docs for full parameters and call examples.
Yes. APIMODELS exposes Qwen3.7 Plus through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.