qwen/qwen3.5-plus

qwen/qwen3.5-plus
VisionToolsJSONReasoning
by qwen

Qwen3.5 Plus — multimodal chat (text/image/video), 1M context, strong coding + agent capability.

ctx1.05M tokens
Max output65.5K
Inputtext + image + video
Outputtext
p50 TTFT2.69 s
INPUT$0.40/ 1M tokens
OUTPUT$2.40/ 1M tokens
p50 TTFT2.69 s7d
p95 TTFT10.00 s7d
TRAFFIC544.0Ktokens / 7d

Qwen3.5-Plus is a large language model (LLM) from the Qwen series developed by Alibaba Cloud's Qwen team. It supports a context window of 1,048,576 tokens and a maximum output of 65,536 tokens. Input…

What is Qwen3.5-Plus?

Who is it designed for?

How does it handle multimodal inputs?

What is the context window size and why does it matter?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="qwen/qwen3.5-plus",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • enable_search
  • enable_thinking
  • include_reasoning
  • logprobs
  • max_tokens
  • n
  • parallel_tool_calls
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • stream
  • stream_options
  • temperature
  • thinking_budget
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Pricing

TierInput / 1M tokensOutput / 1M tokens
256K$0.400$2.40
1.0M$0.500$3.00
Tier selected by input token count of each request

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $10.00

Estimate based on list price

Tiered pricing — this estimate uses base-tier rates.

Token & cost estimator

Input tokens: 20Cost per request: $0.001208

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
2.69 s
Output speed
72.4 tok/s
p95 TTFT
10.00 s
Error rate
3.3%

Public benchmarks

Source: Design Arena

How it compares

qwen/qwen3.5-plusqwen/qwen3-max-previewQwen3.5 397B A17BQwen3.6 35B A3B
Input $/M$0.40$0.86$0.17$0.25
Output $/M$2.40$3.44$1.03$1.49
Context1.0M262K33K262K
Quality8/108/108/108/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

How much does it cost to use Qwen3.5-Plus?
The provided facts do not include pricing information. You should check OrcaRouter's pricing page or contact their sales team for current rates. Costs likely depend on input and output token counts, and possibly on image/video tokens.
What is the context window size?
The context window is 1,048,576 tokens, and the maximum output is 65,536 tokens. This is based on the provided facts.
What are the main strengths of Qwen3.5-Plus?
Its large context window (1M tokens) and support for text, image, and video inputs are the main strengths. This allows it to handle long documents and multimodal tasks in a single API call.
How does Qwen3.5-Plus compare to other Qwen models?
Qwen3.5-Plus has a larger context window (1M vs 128k typical for Qwen2.5) and adds video input. Older Qwen models may not support video. Performance differences are not quantified in the provided facts.
How do I call Qwen3.5-Plus via an OpenAI-compatible API?
Use OrcaRouter's base URL https://api.orcarouter.ai/v1, set the model id to "qwen/qwen3.5-plus", and authenticate with your API key. Send a POST to /chat/completions with the standard OpenAI payload.
Can I use it for free?
The provided facts do not indicate any free tier. It is likely a paid model. Check OrcaRouter's pricing for any available free credits or trial options.
What modalities does it support?
It supports text, image, and video as input modalities. The exact encoding format for images and videos is not specified; refer to OrcaRouter's documentation.
Is there any caching or discount for repeated prompts?
No information about caching is included in the provided facts. Contact OrcaRouter to learn if prompt caching or volume discounts are available.
What are the limitations of Qwen3.5-Plus?
Without benchmark data, its relative performance is unknown. Large context increases cost and latency. The model may suffer from the lost-in-the-middle effect. Multilingual capability is not stated.
Can I use it for real-time video analysis?
Because the model accepts video as input, you can send video frames or segments for analysis. However, processing many frames may consume a large number of tokens, and latency may be high. Real-time use is possible if you limit video length and frame rate.

Embed this badge

qwen/qwen3.5-plus$0.40/M in2692ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/qwen/qwen3.5-plus" target="_blank"> <img src="https://www.orcarouter.ai/embed/qwen/qwen3.5-plus.svg" alt="qwen/qwen3.5-plus on OrcaRouter" /> </a>
Markdown [![qwen/qwen3.5-plus](https://www.orcarouter.ai/embed/qwen/qwen3.5-plus.svg)](https://www.orcarouter.ai/models/qwen/qwen3.5-plus)

Model card as data

GET /api/public/models/qwen/qwen3.5-plusOpen
Machine-readable:/llms.txt/llms-full.txt