Qwen

Qwen3.5-9B

Tool callingStructured outputReasoningImage inputVideo input
Qwen3.5-9B model card cover

Qwen instruction model for multilingual chat, reasoning, and tool use

Context
262K
Released
7mo ago
Parameters
9B
Input / 1M tokens
$0.10
Output / 1M tokens
$0.15

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

EvaluationReported score and source
GPQA diamond
79.0%
Epoch AI · qwen3.5-9B
Epoch AI evaluation
GPQA diamond
78.9%
Epoch AI · qwen3.5-9B_none
Reasoning effort: none
Epoch AI evaluation
OTIS Mock AIME 2024-2025
42.8%
Epoch AI · qwen3.5-9B
Epoch AI evaluation
OTIS Mock AIME 2024-2025
61.7%
Epoch AI · qwen3.5-9B_none
Reasoning effort: none
Epoch AI evaluation
Terminal Bench
9.2%
https://www.tbench.ai/leaderboard/terminal-bench/2.0 · qwen3.5-9B
Agent: little-coder
https://www.tbench.ai/leaderboard/terminal-bench/2.0
Original-source terms apply

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer
Qwen
Model family
Qwen
Type
Language model
Predecessor
—
Successor
—
Released
February 23, 2026
Model ID
qwen/qwen3.5-9b
Openness
Open weights
License
—
Parameters
9B
Input modalities
text, image, video
Output modalities
text
Modality
text+image+video->text
Native context
256K
Tokenizer
Qwen3
Max output tokens
33K
Hugging Face
Qwen/Qwen3.5-9B
Source freshness
Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
Source model
alibaba/qwen3.5-9b
Source family
qwen
Last updated
2026-02-23
Model context
262K
Model output limit
66K
Open weights
Yes
File attachments
Yes
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Temperature control
Yes

Downloadable weights

Complete source record (JSON)
{
  "id": "alibaba/qwen3.5-9b",
  "name": "Qwen3.5 9B",
  "description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
  "family": "qwen",
  "last_updated": "2026-02-23",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 262144,
    "output": 65536
  },
  "release_date": "2026-02-23",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/Qwen/Qwen3.5-9B"
    }
  ]
}

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
Darkbloomdarkbloom/fp4262K$0.08$0.13$0.04—91.82%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

DeepInfradeepinfra/bf16262K$0.10$0.15——99.70%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Parasailparasail/bf16262K$0.10$0.25——100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

SiliconFlowsiliconflow/fp8262K$0.10$0.15——99.13%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Venicevenice/fp8256K$0.10$0.15——100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Togethertogether262K$0.17$0.25——93.26%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware