qwen3.7-maxQwen3.7 Max is Alibaba’s most capable Qwen3.7 model, with top-tier reasoning and agent capabilities, a 1M-token context window, and hybrid thinking (returns 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
Top reasoning + agent performance in the Qwen3.7 line
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 Max is a Large Language Model API provided by Alibaba. Qwen3.7 Max is Alibaba’s most capable Qwen3.7 model, with top-tier reasoning and agent capabilities, a 1M-token context window, and hybrid thinking (returns 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: $2.25, Output: $6.75 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 Max is available through APIMODELS at: Input: $2.25, Output: $6.75 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 Max 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.
Max is the flagship of the Qwen3.7 family, strongest on reasoning and agent work. Plus is the value tier of the same generation: close in capability at roughly a sixth of the price. The rule of thumb is direct: Max for multi-step agents, complex code work, and anything you need right the first time; Plus for bulk, routine and cost-sensitive work. On APIMODELS Max is $2.25 / $6.75 and Plus is $0.36 / $1.44. Same endpoint — switching is a one-field change.
$2.25 per 1M input tokens and $6.75 per 1M output, with cached input at $0.45. Alibaba official USD pricing is $2.5 / $7.5 / $0.5 — so all three tiers are 10% below official. Pay-as-you-go, no minimum top-up, no subscription, and failed requests are never billed. The full 1M-token context bills at the same rates with no long-context surcharge.
POST https://api.apimodels.app/v1/chat/completions with Authorization: Bearer YOUR_API_KEY and body {"model":"qwen3.7-max","messages":[{"role":"user","content":"..."}]}. Plain OpenAI shape, so pointing openai-python or openai-node at base_url=https://api.apimodels.app/v1 works as-is, and so do Cursor and Cline. Add stream:true for streaming.
Reasoning tokens are counted inside completion_tokens and billed at the OUTPUT rate, even though you never see them in the reply. The gap is larger than most people expect: on the sibling Plus model a "write 60 words" prompt returned 3,783 completion tokens of which 3,715 were thinking — roughly fifty times what the visible answer suggests. Three controls: enable_thinking:false skips thinking entirely, thinking_budget caps it, and reasoning_effort selects a depth tier. For simple or bulk work, switch it off.
No Alibaba Cloud or Model Studio account, no real-name verification, no VPN — the endpoint is directly reachable from mainland China. One APIMODELS key also reaches Claude, Gemini, GPT, Grok and every other model on the platform, drawing on a single balance. For most teams that is the real reason to aggregate: not the 10%, but not having to run five vendor accounts and five invoices.
On APIMODELS, Qwen3.7 Max runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Reasoning / Thinking, Agent, 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 Max supports: Reasoning / Thinking, Agent, 1M Context, Tool Calling, Streaming. See the APIMODELS docs for full parameters and call examples.
Yes. APIMODELS exposes Qwen3.7 Max 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.