qwen/qwen3.5-flash

qwen/qwen3.5-flash
VisionToolsJSONReasoning
by qwen

Qwen3.5 Flash — multimodal chat (text/image/video) optimized for cost, 1M context.

ctx1M tokens
Max output65K
Inputtext + image + video
Outputtext
p50 TTFT2.71 s
INPUT$0.10/ 1M tokens
OUTPUT$0.40/ 1M tokens
p50 TTFT2.71 s7d
p95 TTFT10.00 s7d
TRAFFIC1.3Mtokens / 7d

Qwen3.5 Flash is a multimodal language model from the Qwen family, designed for fast inference and low cost. It accepts text, image, and video inputs and generates text responses. Its context window…

What is Qwen3.5 Flash?

Who is this model for?

Key specifications at a glance

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="qwen/qwen3.5-flash",
    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

Input / 1M tokens$0.100
Output / 1M tokens$0.400
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $1.90

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000202

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

Performance

p50 TTFT
2.71 s
Output speed
206 tok/s
p95 TTFT
10.00 s
Error rate
7.3%

Public benchmarks

Source: Design Arena

Community buzz

What developers are saying this week

Hacker News0 mentions · 7d

How it compares

qwen/qwen3.5-flashQwen3.8 Maxqwen/qwen3-max-previewQwen3.5 397B A17B
Input $/M$0.10$2.00$0.86$0.17
Output $/M$0.40$6.00$3.44$1.03
Context1.0M1.0M262K33K
Quality6/109/108/108/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use Qwen3.5 Flash on OrcaRouter?
The cost is $0.10 per 1 million input tokens and $0.40 per 1 million output tokens. This is the provider rate with zero markup by OrcaRouter. You pay exactly what the provider charges, with no additional fees.
What is the context window size?
The context window is 1,048,576 tokens (about 1 million tokens). This includes both input and output tokens across the entire conversation history. The maximum output per generation is 65,536 tokens.
What are the strengths of Qwen3.5 Flash?
Strengths include multimodal input (text, image, video), a very large 1M context window, long output of 65K tokens, low cost per token, and fast inference compared to larger Qwen models. It is ideal for high-volume or real-time multimodal tasks.
How does it compare to larger Qwen models?
Larger Qwen models like Qwen3.5-72B offer higher accuracy on complex reasoning but are slower and more expensive. Qwen3.5 Flash trades some accuracy for speed and cost efficiency, while retaining the same multimodal and long-context capabilities.
Does OrcaRouter mark up the provider pricing?
No. Pricing is passed through at the provider rate with zero markup. You pay exactly $0.10 per 1M input tokens and $0.40 per 1M output tokens for Qwen3.5 Flash via OrcaRouter.
Can I call Qwen3.5 Flash using an OpenAI-compatible API?
Yes. OrcaRouter provides an OpenAI-compatible endpoint at https://api.orcarouter.ai/v1. Use the model ID "qwen/qwen3.5-flash" with your OrcaRouter API key. The request and response formats match OpenAI's chat completions API.
How does data handling work with OrcaRouter?
Data handling policies are determined by OrcaRouter and Qwen. The catalog entry does not provide specific details. Users should review OrcaRouter's privacy policy and Qwen's data usage terms before sending sensitive data.
What modalities does the model support?
It supports text, image, and video inputs. Images can be provided as URLs or base64 data in the user message. Video inputs are typically sent as a sequence of frames (images). The model generates text output only.
Is there a minimum or maximum number of tokens required?
There is no minimum token count. The maximum input tokens (including conversation history) is 1,048,576 tokens. The maximum output tokens per response is 65,536. Use the max_tokens parameter to control output length.
How do I get started calling this model via OrcaRouter?
Sign up for OrcaRouter to get an API key. Set the base URL to https://api.orcarouter.ai/v1 in your code. Use model ID "qwen/qwen3.5-flash" and send a standard chat completion request with your multimodal content. See OrcaRouter documentation for examples.

Embed this badge

qwen/qwen3.5-flash$0.10/M in2705ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/qwen/qwen3.5-flash" target="_blank"> <img src="https://www.orcarouter.ai/embed/qwen/qwen3.5-flash.svg" alt="qwen/qwen3.5-flash on OrcaRouter" /> </a>
Markdown [![qwen/qwen3.5-flash](https://www.orcarouter.ai/embed/qwen/qwen3.5-flash.svg)](https://www.orcarouter.ai/models/qwen/qwen3.5-flash)

Model card as data

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