Qwen: Qwen3.7 Plus

Qwen3.7 Plus is a text generation model from Qwen, the model family developed by Alibaba. It sits in the Qwen3.7 series, and the provider describes it as a cost-effective option within that line. The model was released by the provider on 3 June 2026. Its main category is text, and it is intended for general language work rather than a narrow single task.

The model accepts text and image input and produces text output. That means you can send a prompt that mixes written instructions with images, and the model responds in text. The context window is 1,000,000 tokens, which is large enough to hold very long documents, extended conversations or sizeable code files in a single request. The maximum output length is 131,072 tokens, so responses can be long when the task requires it. Supported request parameters include temperature, top_p, top_k, frequency_penalty, presence_penalty, max_tokens, stop, seed, logprobs and top_logprobs. It also supports response_format and structured_outputs for controlling output shape, tools and tool_choice for function calling, and reasoning plus include_reasoning for models that expose a reasoning step.

Those capabilities point to a few practical uses. The combination of image input and text output suits tasks where a developer needs a written description or extraction from a screenshot, diagram or scanned page. The large context window fits long document analysis, summarisation of lengthy reports, and question answering over big reference sets. Structured outputs and tool calling make it a reasonable choice for pipelines that need machine readable responses or that must call external functions. Reasoning support helps on problems where a step by step pass improves the answer, such as multi part analysis or planning.

You call the model through api14's OpenAI-compatible API using the model id "qwen/qwen3.7-plus". Because the interface follows the OpenAI chat completions shape, existing OpenAI client libraries work with only a base URL and key change. Pass the model id in the request, then set any of the supported parameters listed above, for example temperature and max_tokens for length and randomness control, or tools and tool_choice when you want the model to call functions. The response comes back as text.

One limit worth noting is that output is text only, so the model does not generate images. If your task is purely text with no images and no need for the very large context window, a smaller text model may be simpler and faster to work with.