qwen

Qwen: Qwen3.5-9B

The Qwen3.5-9B is an AI model that can handle multiple input types, including text, image, and video. It has a high context length of 262144 tokens and supports tools, reasoning, and unstructured output. This model may be worth considering for those who need to integrate diverse data sources and have a moderate budget. At $0.1 per million input tokens and $0.15 per million output tokens, it falls in the middle range of pricing. With a blended benchmark score of 19.9 across one independent benchmark, its performance is somewhat established but not extensively proven due to limited coverage.

Open weights 9.65B parameters, about 5.4 GiB at Q4_K_M: fits comfortably on 16 of 18 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 2026-09-23
Output Price
$0.15
per 1M tokens · checked 2026-09-23
Context Window
262,144
tokens

Benchmark results

Independent, published benchmarks. Blended score 18.3 across 1 benchmark, last refreshed 2026-09-23. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 22.5
Model ID
qwen/qwen3.5-9b
Vendor
qwen
Released
March 2026
Tokenizer
Qwen3
Input Modalities
text, image, video
Output Modalities
text
Max Output
32,768 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 $0.15/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 $0.06
A month of a busy support chatbot 5M in / 2M out $0.80

Category rankings

Where Qwen: Qwen3.5-9B places across the 6 categories it ranks in. How we rank →

#CategoryScore
#8 Social Media PostsWriting · of 25 ranked 120
#8 Voice Assistant BackendVoice · of 25 ranked 124
#9 Cheap Bulk InferenceCost · of 25 ranked 137
#18 Customer SupportBusiness · of 25 ranked 128
#21 Self-Hosted / LocalCost · of 25 ranked 117
#21 Real-Time ChatLatency · of 25 ranked 118

Similar models

Quick answers

How much does Qwen: Qwen3.5-9B cost?
$0.10 per million input tokens and $0.15 per million output tokens.
What is Qwen: Qwen3.5-9B's context window?
262,144 tokens, roughly 393 pages of text in a single request.
Does Qwen: Qwen3.5-9B support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Qwen: Qwen3.5-9B process images?
Yes, it accepts image input.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.