Qwen3.6 Flash

qwen/qwen3.6-flash
VisionToolsJSONReasoning
by Qwen · 2026-04-27

Qwen3.6 Flash — multimodal chat (text/image/video) optimized for cost, 1M context, near-flagship capability.

ctx1.05M tokens
Max output65.5K
Inputtext + image + video
Outputtext
p50 TTFT2.00 s
INPUT$0.25/ 1M tokens
OUTPUT$1.50/ 1M tokens
p50 TTFT2.00 s7d
p95 TTFT5.00 s7d
TRAFFIC603.2Ktokens / 7d

Qwen3.6 Flash is a member of the Qwen 3.6 model family from Qwen, designed for efficient multimodal inference. It processes text, image, and video inputs through a transformer-based architecture…

What is Qwen3.6 Flash?

Who should use Qwen3.6 Flash?

What modalities does Qwen3.6 Flash support?

How does Qwen3.6 Flash fit into the Qwen model family?

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/qwen3.6-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

TierInput / 1M tokensOutput / 1M tokens
256K$0.250$1.50
1.0M$1.00$4.00
Tier selected by input token count of each request

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $6.25

Estimate based on list price

Tiered pricing — this estimate uses base-tier rates.

Token & cost estimator

Input tokens: 20Cost per request: $0.000755

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

Performance

p50 TTFT
2.00 s
Output speed
130 tok/s
p95 TTFT
5.00 s
Error rate
2.9%

Public benchmarks

58.0
AA Coding
Better than 85% of models compared
#16 of 106
60.0
AA Intelligence
Better than 85% of models compared
#17 of 110
58.0
AA Math
Better than 36% of models compared
#52 of 81
GPQA Diamond
55.0 index
MMLU-Pro
64.0 index
τ²-Bench
50.0 index
Source: artificialanalysis.ai

How it compares

Qwen3.6 Flashqwen/qwen3-max-previewQwen3.5 397B A17Bqwen/qwen3.5-plus
Input $/M$0.25$0.86$0.17$0.12
Output $/M$1.50$3.44$1.03$0.69
Context1.0M262K33K1.0M
Quality7/108/108/108/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use Qwen3.6 Flash on OrcaRouter?
Specific per-token pricing for Qwen3.6 Flash is not included in the provided facts. Pricing information can be found on OrcaRouter's official pricing page or by contacting their sales team. The cost depends on input and output token counts and may vary based on caching or discounts.
What is the context window size of Qwen3.6 Flash?
The context window is 1,048,576 tokens (approximately 1 million tokens). This includes both input and output tokens combined. The maximum output is 65,536 tokens per request.
What are the strengths of Qwen3.6 Flash?
Based on provided facts, strengths include a 1M token context window, support for text, image, and video input, a high output limit (65K tokens), and fast inference due to its flash architecture. It is ideal for long-context and multimodal tasks requiring low latency.
How does Qwen3.6 Flash compare to the non-flash Qwen models?
Qwen3.6 Flash is optimized for speed and throughput, while non-flash variants (e.g., Qwen3.6 Plus) likely offer better reasoning accuracy. Exact differences in architecture and benchmark performance are not provided. Choose Flash for high-speed applications; choose a non-flash model for tasks requiring deeper reasoning.
Does Qwen3.6 Flash support image and video input?
Yes. It accepts text, image, and video modalities. Images can be provided as base64 or URLs. Video is processed as frames. Audio input is not supported natively.
How can I call Qwen3.6 Flash via an OpenAI-compatible API?
Set the base URL to https://api.orcarouter.ai/v1 and use the model ID "qwen/qwen3.6-flash". Authenticate with your OrcaRouter API key. The API is fully OpenAI-compatible for chat completions.

Embed this badge

Qwen: Qwen3.6 Flash$0.25/M in2000ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/qwen/qwen3.6-flash" target="_blank"> <img src="https://www.orcarouter.ai/embed/qwen/qwen3.6-flash.svg" alt="Qwen: Qwen3.6 Flash on OrcaRouter" /> </a>
Markdown [![Qwen: Qwen3.6 Flash](https://www.orcarouter.ai/embed/qwen/qwen3.6-flash.svg)](https://www.orcarouter.ai/models/qwen/qwen3.6-flash)

Model card as data

GET /api/public/models/qwen/qwen3.6-flashOpen
Machine-readable:/llms.txt/llms-full.txt