We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Qwen: Qwen3.5-9B
qwen/qwen3.5-9bTry Qwen: Qwen3.5-9B now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
Qwen: Qwen3.5-9B at a glance
- Input price is 82% lower than the median of 434 Text models.
- Context window of 262,144 tokens, enough for long documents and multi-turn conversations.
- Supports tool (function) calling for agents and integrations.
- Supports structured JSON output with a schema.
- Supports reasoning effort control.
- Accepts images as input (vision).
- A typical request (1,000 input / 500 output tokens) costs about $0.000508.
About Qwen: Qwen3.5-9B
Qwen: Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, developed by Qwen. It is built as an efficient 9B-parameter architecture that combines reasoning, coding, and visual understanding within a single model, using a unified vision-language design. It sits in the text category on api14, and its provider release date is 10 March 2026.
The model accepts text, image, and video inputs, and it produces text output. Its context window is 262,144 tokens, with a maximum output of 32,768 tokens. That combination of a large context and mixed input modalities means it can work over long documents while also grounding its answers in visual material, such as screenshots, diagrams, or video frames, rather than text alone.
Practical uses follow from those capabilities. Long-context reasoning over large text corpora is a natural fit, as is code assistance, since the model is designed for coding tasks. Because it accepts images and video alongside text, it can also support tasks such as describing or answering questions about visual content, extracting information from screenshots, or reasoning over material that mixes prose and imagery. The 32,768-token output ceiling allows for substantial generated responses, not just short replies.
You call the model through api14's OpenAI-compatible API using the model id "qwen/qwen3.5-9b". The request parameters it supports are frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, and top_p. Tool calling and structured outputs are available through the tools, tool_choice, and structured_outputs parameters, and reasoning behaviour can be influenced with reasoning and include_reasoning.
If your workload is text only and does not need image or video input, a text-only model may be a simpler fit, though Qwen3.5-9B handles text as well. If you need output modalities other than text, this model does not provide them, since text is its only output modality.
How to call the Qwen: Qwen3.5-9B API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "qwen/qwen3.5-9b".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "qwen/qwen3.5-9b",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pSpecifications
- Context length
- 262,144
- Max output
- 65,536
- Input
- text, image, video
- Output
- text
Requests on api14 · last 7 days
Qwen: Qwen3.5-9B: frequently asked questions
- How much does the Qwen: Qwen3.5-9B API cost?
- Qwen: Qwen3.5-9B costs Input $0.28 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Qwen: Qwen3.5-9B?
- Qwen: Qwen3.5-9B reads up to 262,144 tokens per request: prompt, history and documents together. It writes up to 65,536 output tokens per response.
- What can Qwen: Qwen3.5-9B do?
- Qwen: Qwen3.5-9B accepts text, image, video and returns text. It supports tool calling, structured JSON output, reasoning effort control.
- How do I call Qwen: Qwen3.5-9B from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "qwen/qwen3.5-9b". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Qwen: Qwen3.5-9B?
- Comparable Text models at a similar price: Microsoft: Phi 4, DeepSeek: DeepSeek V4 Flash Latest, Z.ai: GLM Flash Latest. Each runs through the same API key, so switching is one string.
Qwen: Qwen3.5-9B community
New topicThis community has no topics yet. Open the first one about Qwen: Qwen3.5-9B.