qwen

Qwen: Qwen3.6 35B A3B

Qwen is a large language model developed by qwen that supports multiple input modalities, including text, image, and video. It has a high context length of 262144 tokens, allowing for detailed analysis and understanding. Qwen also provides tools to aid in tasks such as reasoning and supports the use of external tools. Qwen may be worth considering for those on a budget due to its relatively low input price per million tokens at $0.1. However, it lags behind other models in terms of benchmark performance, with a blended score of 42.9 across three independent benchmarks. Its high output price per million tokens at $0.9 may also be a concern for those planning to rely heavily on the model's capabilities.

Open weights 36B parameters, about 20.1 GiB at Q4_K_M: fits comfortably on 1 of 17 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
100/100
price + capability + benchmarks
Input Price
$0.10
per 1M tokens · checked 2026-09-09
Output Price
$0.90
per 1M tokens · checked 2026-09-09
Context Window
262,144
tokens

Benchmark results

Independent, published benchmarks. Blended score 42.9 across 3 benchmarks, last refreshed 2026-09-09. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 36.7
AI Index Coding software engineering tasks 69.1
AI Index Agentic multi-step tool-using tasks 24.8
Model ID
qwen/qwen3.6-35b-a3b
Vendor
qwen
Released
April 2026
Tokenizer
Qwen
Input Modalities
text, image, video
Output Modalities
text
Max Output
235,929 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.10/M input and $0.90/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.10
A month of a busy support chatbot 5M in / 2M out $2.30

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-08-28 $0.10 $0.90 262,144
2026-08-17 $0.14 $1.00 262,144
2026-08-09 $0.15 $1.00 262,144
2026-07-17 $0.14 $1.00 262,144

Similar models

Quick answers

How much does Qwen: Qwen3.6 35B A3B cost?
$0.10 per million input tokens and $0.90 per million output tokens.
What is Qwen: Qwen3.6 35B A3B's context window?
262,144 tokens, roughly 393 pages of text in a single request.
Does Qwen: Qwen3.6 35B A3B support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Qwen: Qwen3.6 35B A3B process images?
Yes, it accepts image input.